They seem to distance themselves from binaural beat technology, in their About Us page: "Gerald Oster, the original researcher of binaural beats, denied it's therapeutic use cases and endorsed other audio methods as more effective"
$7/month doesn't seem too bad, at least to test out. I think I will give it a go for a bit.
The website is a bit vague about that, but they say it has nothing to do with binaural beats.
> How is this different from binaural beats (or similar tools)?
> Binaural beats is 1970s technology. It's akin to comparing dial up internet (binaural beats) to fiber optic internet (Brain.fm). The difference is advanced technology which equates to superior results. Gerald Oster, the original researcher of binaural beats, denied it's therapeutic use cases and endorsed other audio methods as more effective find the research paper on google. [1]
> Why are binaural beats so popular? They've been overhyped by marketers, not scientists.
There's another method that shifts the phase of the entire spectrum instead of generating pure tones. That method has been available in software like CoolEdit (I think Adobe bought it later) since at least 1996. I wonder if that is the method used by brain.fm, but I haven't had a chance to check it out.
Hi there, we don't use binaural beats. Or isochronic tones.
Our CTO (Adam Hewett) is the founder of Transparent Corp. His older software is used to create the vast majority of isochronic tones, and all those videos you see on youtube, etc.
Any rhythmic audio stimulus will entrain the brain. Actually, the very first research on audio brainwave stimulation used simple clicks. As another example if you had a drummer that could be precise enough, drums could also stimulate the brain.
But, neither clicks nor binaural beats nor isochronic tones sound very good. Yes, you can get used to them. Adam used them for a decade. But he spent all of that decade finding a better way.
And what he found is that if you embed rhythmic modulations into the music in a natural way - disguising it as natural vibrations or vibrato or tremolo - not only is it more pleasant, it is more effective. MUCH more effective. The intensity levels we can get using this method are much higher than what we can get with older methods and still be comfortable for the user.
So in 2005 Adam created a system that could single out instruments in a recording and add natural-sounding "vibrations". He has been perfecting it ever since.
There's a lot more to Brain.fm as well! We've perfected MIT's HRTF technology to create a kind of "3D audio". And that's the real reason we suggest using headphones for the full effect of Brain.fm. It is a vital part. We spatially place sound around you to enhance your goal (for focus it is in front of you, for sleep it mimics the rocking of a hammock, cradle, etc).
And then there's the algorithmic AI-generated music. Believe it or not, all the music in Brain.fm is produced by an algorithm that Adam spent a very long time.
The benefit? Imagine a rain sound for a second. Hundreds of thousands of drops! Imagine now that each and every drop is synchronized to the purpose of the stimulation. Now imagine a symphony... That is Brain.fm.
I'll have Adam hop in the thread soon so we can answer any further questions!
Can you provide evidence of the effectiveness of your methods? Are there peer reviewed studies that sustain your statements? Spot checking the site, there isn't much convincing evidence (a double blind trial with very few subjects that you sponsored is not really convincing).
The sounds are unusually good for algo music, which typically has very poor production values.
I doubt you've perfected HRTF, because everyone has a different HRTF, so you'll always get an approximation at best.
>Imagine a rain sound for a second. Hundreds of thousands of drops! Imagine now that each and every drop is synchronized to the purpose of the stimulation. Now imagine a symphony... That is Brain.fm.
This is marketing. As a statement about technology or user benefits, it's meaningless.
To be fair, I liked the audio a lot, and it's the best algo-comp effort I've heard yet.
The literature on entrainment seems unclear. There are a few studies about binaural beats I know of. There's not a lot in mainstream neurological journals - just in a few fringey publications - although this may have changed since I last looked.
I think if you're claiming AI-created symphonies of brain stimulation you're going to have an easy sell to the New Age demo, and a very tough sell to a lot of other demos.
Thanks much for saying that you like the audio! You seem to be into this stuff so that's high praise.
Some clarifications:
> Imagine a rain sound... synchronized to the purpose.. marketing, benefits, etc
Sorry, you're right, that was just a miscommunication. We're all a bit stressed here - didn't expect this much attention.
So part of what we're doing in Brain.fm is using synchronized modulations (pulses of sound) to affect the brain. You're right, the literature on BWE could be better, mainly because binaural beats are so well-known, and so they keep getting studied, which is unfortunate because they're not all that effective. We don't use them at all. Northwestern actually studied a bunch of major bbeat brands and couldn't detect any effect at all (at least for delta). So when I approached my friend Giovanni with a sleep protocol he was understandably skeptical, but the results as you can see on our site, are pretty damn impressive. He's now our lead neuroscientist, but still works for Northwestern too. There's a lot more to that story but I don't want to type more of a novel than I already am :)
Actually... to be honest I'm not sure I even like the name "entrainment" - Giovanni has a better theory having to do with neuron "recruitment" that is simpler and has more explanatory power. Here's the thing: any repetitive audio stimuli produces a corresponding response in the brain, provided it is consistent enough, rapid enough, and lasts long enough. Bbeats supposedly work because of the "beat" part. But these days, we can easily create beats using all kinds of methods, like modulation, where we can adjust the waveform, adjust the phase on the fly, target frequency ranges, and so on, all of which are super important it turns out. Plus - as she mentioned - we can synchronize all the other elements in the song to the same "beat." All while monitoring the effects using an EEG.
Hope that helps clarify some things. Hey, I know it seems far out, so I'm happy to answer any questions. Giovanni will hopefully be on here tomorrow. I think a podcast, video, or something with the two of us explaining this stuff is long overdue.
Anyway, thanks again! Hope you come back and and we can talk some more about it.
"That is generally where the science ends and the pseudoscience begins. A number of companies and individuals have then extrapolated from the phenomenon of entrainment to claim that altering the brain waves changes the actual functioning of the brain. There is no theoretical or empirical basis for this, however. Entrainment is a temporary effect on the synchronization of neuronal firing – it does not improve or increase brain functioning, it does not change the hardwiring, nor does it cure any neurological disorder. There is no compelling evidence for any effect beyond the period of entrainment itself."
I do like the "Cyberpunk" atmosphere of some of the music. But their other claims require some extraordinary evidence.
For example, does this impart any more benefit than me listening to my favorite working music whilst working? It doesn't seem to. But I haven't had a chance to sift through their supposed "180 studies"
Neurological disorders are often related to periodicity of body rhythms and I think its generally accepted that resonance theory on internal oscillators are still in an infant stage, especially regarding their long term and cross cultural capability for variance. All the promises stated are possible.
But, I'd also like to see a simple summary of the theory underpinning this music, even just defining the type of entrainment would make the product far more interesting and valuable.
This coupled with the in-your-face-sales, promises and gimmicks whilst casually alluding to studies (with no reference for technical points) makes me get the feeling I'm being duped.
Yeah, I'd also like to see a study where they test this magic-AI-music against some generic 10 hours relax/focus music from Youtube (or the Machinarium or Age of Empires 2 soundtrack). Properly randomized and blinded etc.
I'd also like to know what it means that this is produced by an AI. What do they optimize for? I mean it would be really cool if they could do some reinforcement learning with real time EEG feedback and whatnot, but I think there is not much AI going on here. Perhaps even zero.
Also, the UI contains a lot of bullshit frills and wizardry, writing stuff like "generating your brainwave" and shiny animations (It's like how MSN messenger used to write "Loading your friend list..." and other recognizable and understandable things for half the time of its loading screen).
And then after one session it makes us click through a personal survey, where you have to click yes or no, for questions like "are you easily distracted", "do you have problems with concentrating", "do you have issues with personal organization" and similar stuff, do you have anxiety etc etc. It's a bit like they are trying to make you realize that "yeah, kinda, I think I could improve myself in these things, let's click yes". I'm not sure how they call this psychological manipulation technique, but I've read about it somewhere. Basically it's the same idea as some cashiers being instructed to ask you if your shopping was a pleasant experience. You want to be polite and go on with the script, but then you'll still identify with that "yes" answer.
Generally, the site rubs me the wrong way. It seems to be targeted at people who don't know much about science or AI, but like the brand and image of science and AI, as these are cool things nowadays. It also builds upon gamification and all these manipulative things.
> "I'm not sure how they call this psychological manipulation technique"
You could see this personal survey as a way for the site to make you doubt or question yourself subconsciously. For you to even read the question, you have to process that question introspectively. The more questions you answer, the more likely you'll find something you'll want to improve. Then miraculously this site is the silver bullet. Buy more sessions here [enter credit card info].
Another way you could see this product, the survey, and the upsell could be through the perspective of NLP (Neuro-linguistic programming). The two concepts to focus on would be pacing and leading. You listen to the relaxing ambient music and you become calm. (Pacing) Afterwards the survey pops up when you're in a more docile state. You answer these questions. Each of which is ever so slightly leading you to the conclusion that this product is the solution to the problems you've clicked "Yes" to.
It's called "commitment and consistency" among Cialdini's six principles of influence (in "The Psychology of Persuasion", which I believe is sort of a classic)
> [no evidence that] altering the brain waves changes the actual functioning of the brain
That post was from a while ago, so I'm not sure if he's updated his opinion, but there's plenty of evidence that changing brain waves affects the functioning of the brain. I feel I should have Giovanni respond to that specifically so I'll get him on here as soon as he's available.
> There is no compelling evidence for any effect beyond the period of entrainment itself.
There is evidence for it, but at any rate we're not claiming that. We're helping people sleep or relax while they listen, helping them focus while they listen.
> does this impart any more benefit than me listening to my favorite working music whilst working?
I'd be super interested to find out! In the study we did on our focus sessions, we compared very similar music - still generated by the AI actually. We have the unique ability to create a sham that sounds nearly identical to the experiment, due to the way we "disguise" the stimulation as vibrato, tremolo, normal instrumental vibrations, electronic LFOs, and so on. So we opted for that instead of letting them choose something from spotify, etc. I actually think we would have gotten a much greater result in that case, because the AI-generated music - although not containing "entraining" modulations - still obeyed rules designed to keep the music from being distracting (no lyrics or abrupt stops, volume consistency, avoiding certain frequency ranges (pitches), and so on). Even so, if you find your existing music to work, why switch? Give both a try, see what you think, base your decision on results. Or use both, depending on how you feel? Today I coded to Queen and then Brain.fm and then some Motown. I especially love video game soundtracks like Chrono Cross, WarcraftIII, Wipeout... Brain.fm is there if I need an extra boost.
I'd love to hear what you listen to? Kind of a hobby of mine to collect people's work music :)
Sure! I spent some time looking through my library. Here's some, but there are more. There's some I really wanted to show you but will take more time to get the actual reference. Sorry, if you're interested, please email us when all this craziness is over :) Also apologies about the lack of consistent formatting or alphabetizing :)
Oudiette, D., G. Santostasi, and K.A. Paller, Reinforcing rhythms in the sleeping brain with a computerized metronome. Neuron, 2013. 78(3): p. 413-5.
Santostasi, G., R. Malkani, B. Riedner, M. Bellesi, G. Tononi, K.A. Paller, et al., Phase-locked loop for precisely timed acoustic stimulation during sleep. J Neurosci Methods, 2016. 259: p. 101-14.
Tononi, G., B.A. Riedner, B.K. Hulse, F. Ferrarelli, and S. Sarasso, Enhancing sleep slow waves with natural stimuli. . Medica Mundi, 2010. 54(2): p. 73–79.
Joyce, M. and Siever, D., 2000. "Audio-Visual Entrainment (AVE) Program as a Treatment for Behavior Disorders in a School Setting." Journal of Neurotherapy. 4, 9-25.
Berg, K., and Siever, D., 2009. "A controlled comparison of audio-visual entrainment for treating Seasonal Affective Disorder." Journal of Neurotherapy 13.3 (2009): 166-175.
Ossebaard, H. C., 2000. "Stress reduction by technology? An experimental study into the effects of brainmachines on burnout and state anxiety." Appl Psychophysiol Biofeedback. 25, 93-101.
Huang TL1, Charyton C. 2008 A comprehensive review of the psychological effects of brainwave entrainment. Altern Ther Health Med. 2008 Sep-Oct;14(5):38-50.
R Olmstead Use of auditory and visual stimulation to improve cognitive abilities in learning-disabled children. Journal of Neurotherapy, 2005
Ong, J.L., J.C. Lo, N.I. Chee, i.G. Santostas, K.A. Paller, P.C. Zee, et al., Effecsts of Phase-Locked Acoustic Stimulation During a Nap On EEG Spectra and Declarative Memory Consolidation.
Ngo, H.V., T. Martinetz, J. Born, and M. Molle, Auditory closed-loop stimulation of the sleep slow oscillation enhances memory. Neuron, 2013. 78(3): p. 545-53.
With photic stimulation:
San Martini, P., Venturini, R., Zapponi, G. A. and Loizzo, A., 1979." Interaction between intermittent photic stimulation and auditory stimulation on the human EEG. Preliminary investigation through power spectral analysis." Neuropsychobiology. 5, 201-206.
Kumano, H., Horie, H., Kuboki, T., Suematsu, H., Sato, H., Yasushi, M., Kamei, T. and Masumura, S., 1997. "EEG-driven photic stimulation effect on plasma cortisol and beta-endorphin." Appl Psychophysiol Biofeedback. 22, 193-208.
Nomura, T., Higuchi, K., Yu, H., Sasaki, S., Kimura, S., Itoh, H., Taniguchi, M., Arakawa, T. and Kawai, K., 2006. "Slow-wave photic stimulation relieves patient discomfort during esophagogastroduodenoscopy." J Gastroenterol Hepatol. 21, 54-58.
Solomon, G. D., 1985. "Slow wave photic stimulation in the treatment of headache--a preliminary report." Headache. 25, 444-446.
Budzynski, T., Jordy, J., Budzynski, H., Tang, H. and Claypoole, K., 1999. "Academic Performance Enhancement with Photic Stimulation and EDR Feedback. Journal of Neurotherapy." 3, 11-21.
Patrick, G. J., 1996. "Improved neuronal regulation in ADHD: An application of fifteen sessions of photic-driven EEG neurotherapy." Journal of Neurotherapy. 1, 27-36.
Thanks, glad you like it. There's a piece of my soul in that thing. Or I assume soul-transfer is what happens when you go full hermit for 5 months and gain 50 pounds creating something like this.
Any questions about the science or AI, happy to talk about it. :)
Good for you, but that's none of my business. I don't want to be harsh, but I don't like this kind of emotional manipulation. You're trying to prime me to be buddies with you and cut you some slack.
I have some questions. In what sense is this an AI and not simply a computer program? Did you use methods that are discussed in AI or machine learning textbooks and conferences, or did you simply put the cool label AI on what is essentially "just" a hand crafted algorithm?
I know there is no clear separation as AI is a subset of algorithms, but still I feel some dishonesty going on here.
Also in other comments by the company, I can see the attitude about the science that (not precisely quoted) "we're not sure yet, we're excited to find out" and "give it a try and compare it to other music how it goes for you" etc. Well, no. You're making the claim that there is some solid science going on behind this, that you have more than a dozen studies and you put pretty, science-y charts on the website. Now I'm not saying that it doesn't work, but please show me the peer reviewed randomized double blind studies that show altered brain waves and some significant quantitative change (preferably not only self-reported things about how they "feel"). Preferably there should be different groups: no music, generic pop music, normal ambient music, some baseline of your company's music and finally the specially crafted fully optimized version of your company's music.
Until I can see that, verified also by someone who's not paid by the company, I'll have my doubts.
Someone poured their heart and soul into something that may not make a profit! Don't be such a cranky scrooge just because they confess that.
An ex used to run neurological studies, and they are incredibly expensive. The small survey groups will no doubt improve with time. If you don't believe the hard science, then try the product and see if it works for you compared to the music that's linked to in the above posts. Further criticism is unwarranted.
> Someone poured their heart and soul into something that may not make a profit!
Sorry but that's irrelevant. A homeopathy practitioner could say the same thing.
Their site front page says in big font: "Dramatically improve focus, relaxation & sleep". And it says science all over the place and contains pretty sciency charts. An intentionally wide range of charts. Vertical and horizontal bar charts, pie charts, line graphs, all to make you go "this looks legit science!"
So where is the peer-reviewed, randomized, controlled, double blind trial to support these claims? The only study that tries to compare it with placebo music seems to be unpublished as of yet and all we can see is some charts. We don't see their methodology, the results, significance etc.
I would have no problem with this if they didn't brand it so extremely heavily on science.
We're planning on following that one up with a more robust study, because our users do get great results with HRV and it's an interesting topic.
One of our former neuroscientists published a well received meta analysis in a journal, but it's a bit outdated now re: what we're doing. Still, it's on our site if you're interested.
And then of course here's our own research that is pending publication:
We also do regular analysis of user progress with a few statisticians I work with, and those will be published as well. Sorry, just takes time to get these things ready and through to a journal. Trying our best though. :)
I appreciate your honesty here. If I'm reading it right, result of the focus study is that the Music-Placebo difference is at p=0.044, 0.041, 0.048. So it is significant (under 0.05) but "just barely", which is always a warning sign, especially if the study was done and published by the company itself.
It's actually a very very good result for the tests we did. A similar study using a boatload of caffeine couldn't reach statistical significance. Also I believe strongly that if we'd compared it to say, classical music or some random ambient album, it would have been an even stronger result. The placebo in this study was still generated by the AI, so it followed the same rules - rules that naturally help people focus. The only thing it lacked was the brainwave stimulating modulations. We did see a big difference on an EEG because of that, but the fact is that part of what makes the sessions work is that they follow strict rules, and there's nothing wrong with that. It just makes it harder in this case.
But I actually like it like that. I want a double blind study with identical-sounding placebo and more subjects. After that we can study how it compares to regular music commonly used as study-aids.
Regarding the statistical analysis, result interpretation, etc, I feel I should let Giovanni himself defend his paper. He's dealing with family / health issues right now, but I hope to get him on here as soon as possible. I promise he will respond eventually and clear this up.
> I believe strongly that if we'd compared it to say, classical music or some random ambient album, it would have been an even stronger result.
Strong beliefs like that are still just hunches.
> I want a double blind study with identical-sounding placebo and more subjects. After that we can study how it compares to regular music commonly used as study-aids.
My problem is that you already decided that it "dramatically improves focus, relaxation and sleep". What if the new better study doesn't show the effect? Will you dissolve the company? Will you just change the marketing?
I'd also suggest "triple-blinding" the study, i.e. the person who does the statistical analysis on the computer should also not know which music was which.
Hey, no problem. Not trying to "prime" you here, this is just how I talk. I'm not that strategic. If you think it would help, I'd be happy to get on a call/skype? I just feel like there's some miscommunication going on here and I'd like to clear it up if I can.
The pretty charts you see are direct copies of the EEG analysis by Giovanni. We did try to make them pretty, but if you're interested in the originals check out the analyses Giovanni did. He'll be on at some point to explain them further if you want to direct some questions to him directly.
3) Your study procedure recommendation
Regarding your study procedure recommendation, that's a great idea. We did something very similar to that in the Focus analysis above. 3 conditions: No Music - Music Without Stimulation (placebo) - Music With Stimulation. To the untrained ear, the music was indistinguishable. Most people can't tell which is which, and the feedback we got from the subjects confirmed it. It was actually really interesting: some of them asked to be able to keep the placebo-music (not calling it that, obviously), saying they worked better on it, when their results often told a different story.
Next study will be double blind and have more subjects. Giovanni feels we have enough information now to do it right.
So, someone above asked about the AI thing and I'm happy to explain it. I'll paste a lot of that below. Although I have to say I'm not sure what textbooks are calling anything these days. When I talk to programmers right out of college sometimes there's a bit of confusion as they talk about patterns I know, but use different names. I grew up programming on an 8088, and I've been working for myself for 13 years, mostly by myself, so I'm sure I'm behind on a lot of things.
Having said that, I'd probably call what I'm doing "Emergent" because there are many competing little pieces. Let's see if I can explain it quickly here, though please don't be too hard on me I'm trying my best to answer a lot of questions, but I'm really happy to go more into later after all this dies down :) Conceptually, you could think of it as first creating what I'll call "song-bot", which acts a kind of overlord, and has some instructions from me (like maybe there's some specific chords I want it to use, keys to avoid, tempo, brainwave protocols, genre, etc, etc). This song-bot guy then spawns a bunch of little other bots that compete with each other for the right to play/fade in/or generally be a part of the final result. These little guys have different characteristics, like a "drum-bot" might has different places it "wants" to be placed, and so generally competes with other drums, but not always. Sometimes I'll even have little "bots" for individual notes of a certain instrument. They obey certain rules of course, to form a background, drum line, or a simple me...
> If you think it would help, I'd be happy to get on a call/skype? I just feel like there's some miscommunication going on here and I'd like to clear it up if I can.
Nah, no need. I can't say much more than what I said already. As a computer science major who took AI and machine learning courses and as a self-identifying scientific skeptic, I just felt the need to point out the fishy things going on here. Anyone here can read your reactions as well and build their opinion.
Me as well. Some of the tracks (or rather the instruments that seem to show up regularly) are starting to build some muscle memory to at least trigger my brain to start focussing.
I'm sure that most of the benefit of using this tool is derived from the fact that the music is consistently low-tempo and relaxing ambient music. Comparing that to an album of ambient music, it might not be so consistent in its style and so could distract from the focus.
Still, the generated music is quite nice. I still feel that I'd rather listen to a real album, though, created with artistic intent and not computer generated. Music (as a listener and creator) is very important to me and I'm not ready to concede its creation to the machines just yet. Perhaps in a few more years...
Hey, this Adam from Brain.fm. I created the music "AI" thing.
Glad to have the praise of a musician! My family's very musical, so it took some convincing for them as well.
The thing is, it still takes creativity! It took me half a year to create it, and there's a little piece of my soul in this AI.
A horcrux, programmed in. :) It makes music how I would make music. Well, most of the time.
I had to create the thing because it was taking me a month to create a single session manually, and much of what I had to do was so precise that an algorithm could do it easier. Every note, every beat, has to be perfectly synchronized with the other filters we're applying to the music. So I built some algorithms, but they piled up, had to be constantly re-calibrated based on additions to the music as I kept composing. Keep in mind these are half hour to hour long pieces! And there's no shortcuts - I can't just throw a bunch of music in there, because even the smallest pop/overclip/dissonant moment, could wake someone up, or break their concentration... It just got to a point where something with more working memory than me had to take over.
The music in Brain.fm is very structured and obeys strict rules. There are some genres I can't get right yet - rock, folk, and so on. Although I'm always happy when people like it, and I like to think I did a good job giving the AI decent taste, I definitely don't have any illusions about this replacing humans :)
Did you take a listen to the Focus categories? Most of those are 120bpm. (skip around till you hit the classical one - I fed the AI harpsichord concertos I grew up with. Cool example of how maybe this could help some composers!)
Got a link to your stuff? Love to hear it.
- Adam
(oh and also there is definitely more than ambient music even in the relaxation sessions. Give it another listen if you have a moment. Skip around. There's indian music, mongolian chants, and the nature sounds are also all AI-generated. Every gust of wind, every raindrop :)
Since you mentioned "the smallest pop", I thought you might be interested to know that the volume slider causes discontinuity pops, at least on Firefox, and could benefit from some smoothing.
Ahh! Damnit! I did not know that, sorry. Audio playback is remarkably inconsistent between browsers, or even between the same browser versions in different environments. It's a big headache.
It is proprietary I guess, but I don't really mind talking about it :) I did a talk recently at Northwestern (The Garage) and they were interested, so I spilled the beans. I'd like to get that talk up actually.
I used the Bach's harpsichord concertos - Allegro/Presto/etc, since we're doing focus in that case. It's actually the 2nd most popular theme on the site! I made that one for myself to be honest - I grew up with those things and it was a labor of love, that one. Took some major reconfiguring, but it was worth it I think.
You're definitely not listening to the same thing each time. There's a huge variety. It doesn't generate the sessions in real-time (audio processing of this kind is very, very CPU intensive), but we take the data we get and process it for later use. At this point there's so many sessions "cached" that you get huge variety right off the bat and we're building up an infrastructure to create more sessions faster
I'll be adding more "themes" later. To explain, in some cases there are sessions that use a specific protocol, like the harpsichord one. That's static. But other themes are more flexible, and so different protocols can be used for the same theme. By protocol I mean what we're actually trying to stimulate in the brain.
Some people here have questioned the science behind the claims of focus and relaxation etc, but even without that as a product feature what you're making is pretty awesome.
I can imagine a product where you can combine a bunch of composers and genres and it'll just write songs for you to listen to :)
I'm signing up just to listen to the music your thing makes!
P.S. I played a few Bach pieces while learning Piano, he's one of my favourite composers!
Hey, thanks! I appreciate that. I played classical guitar as a kid - still do. And Bach is definitely a favorite, though one of the most difficult. You just know he composed those lute pieces on his damned organ, where he could use 2 hands and 2 feet ;)
Yeah, I have to say it has not been a great experience here at HN. But, maybe I'll win them over yet. After 13 years, we're finally taking off, and the first thing I did was pour everything in the science, so we'll be there soon.
Well, enjoy Brain.fm! And feel free to drop me a line with an update any time.
What makes you use the word "AI" as opposed to "algorithm"? What kind of AI techniques do you use just broadly speaking (I mean techniques that are described in AI textbooks, AI courses, AI conferences)?
Sure! Happy to explain it. Although I have to say I'm not sure what textbooks are saying these days. When I talk to programmers right out of college sometimes there's a bit of confusion as they talk about patterns I know, but using different names. I grew up programming on an 8088. :)
In a podcast called College Info Geek and recently in I did a talk at Northwestern (The Garage) and I called what I'm doing "Emergent" because there are many competing little pieces. Let's see if I can explain it quickly here, though please don't be too hard on me I'm trying my best to answer a lot of questions, but I'm really happy to go more into later after all this dies down :) Conceptually, you could think of it as first creating what I'll call "song-bot", which acts a kind of overlord, and has some instructions from me (like maybe there's some specific chords I want it to use, keys to avoid, tempo, brainwave protocols, genre, etc, etc). This song-bot guy then spawns a bunch of little other bots that compete with each other for the right to play/fade in/or generally be a part of the final result. These little guys have different characteristics, like a "drum-bot" might has different places it "wants" to be placed, and so generally competes with other drums, but not always. Sometimes I'll even have little "bots" for individual notes of a certain instrument. They obey certain rules of course, to form a background, drum line, or a simple melody, and then they pass that information along to subsequent incarnations (there's some learning involved in that process, though I hesitate to give it any textbook term - man, you have me terrified here of defining something wrong! :) ). Through that learning, the pattern the original little guys made has more weight and will tend to repeat. But again, not always.
After a while, a song... emerges. A kind of "emergent intelligence."
The resulting song can be quite complex and varied. Of course there's more to it, because songs have sections, but all in all the genres I'm using are very structured. Techno especially, is very easy for the AI. Sometimes I'm tasked with creating a theme in a particularly difficult genre, and that's when it gets really tricky/fun (such as some of the Indian ones, which were labors of love). In these cases, I may have to re-rerun many "generations" of the AI through the same song from beginning to end, with different parameters/instruments, but with the same patterns/learning, because what can happen in these cases is that it starts out simple, and increases in complexity as it goes, so the start can sometimes be a bit boring.
Also keep in mind this is just a conceptual explanation. The code is much less amusing. Thinking of naming processes "bots" though just for fun.
I hope I explained it OK. Listen, I'm not saying it's Watson or anything, it's really just a necessary step I had to take in order to make the computer do what I wanted it to do. I tried out some different ideas, and this one worked the best. I like the result at least :)
That's fine and makes sense. I wouldn't call it AI though.
The marketing is just too overhyped and in-your-face for my taste. It reminds me of the startup called "The Grid", which claimed they will build a website-creating AI. It's an often misused term in marketing.
Another cool mystery term is precisely "emergent". Okay I'm not trying to be harsh on you, and I know that marketing is all about exaggeration and wooing people into buying your product and having the right keywords so that tech news portals pick up on you and can produce a clickbaitish title etc. Also it may enhance the placebo effect in such soft areas as this.
Anyway, I do like how it actually sounds and it seems to have worked on me somewhat, but I'm not too sure about that or how much of it is placebo.
We're not using that term anywhere in the marketing either.
This is just me talking here man. I'm not a marketer, or even really a good businessman. I did this for 13 years and we're just now taking off. I do music and programming, that's it. :)
But I do think Junaid did a great job on the site. Yeah there's more work to do, always is.
Sure, this probably helps you focus better than a standard studio album.
I would argue that 90% of the benefit of this music is just from the extended intervals of contiguous playing, so there's no "break" disruption. I think any DJ (esp. deep house) worth half their salt can get someone "in the zone" for half an hour at a time. And artists devoted to minimalist ambient or trambient can get you going for hours straight.
Honestly the "Focus: Intense" or whatever I find super annoying. It's got this constant anxious buildup feel to it and never fucking breaks into what I would consider that peak when I start playin my keyboard like a goddamn piano.
Basically, no fucking way would I even consider shelling out an additional Spotify subscription for some "high tech" whale song machine.
The feeling you described reminds me of the genre "jersey club" -- you can spend hours in a buildup that never breaks into a drop. Absolutely horrific, I don't understand the genre at all.
For the productivity obsessed on HN making negative comments, I'm surprised more haven't tried this kind of stuff out.
I have used white noise or waves for a long time to drown out outdoor noise around me.
My initial start with this kind of stuff was listening to various stations on somafm.
I like finding music that fits well in the background, isn't too engaging or something I'm familiar with, and hopefully devoid of vocals so I kept looking and came across a few instrumental tracks on itunes.
There's maybe a reason babies benefit from wave/sleep machines. White noise does have an effect that can aid in focus and concentration, science, placebo, or otherwise, I'm happy for the sustained productivity boost I've been able to have for several years.
I did buy brain.fm on a whim a while back it has replaced simplynoise or more to that point. If there was a bit more information published on how it was put together I'd be interested, and if not, I'd probably keep using it.
Would like it to be a downloadable or app that I could keep with me. Some things aren't for those who can't put themselves in other people's shoes, or imagine something may work for others that doesn't seem to be imaginable or work for them.
I have been using this the past few months, there is some repetition but not enough to notice. It seems brain.fm is keeping track of what it does and doesn't play for me and asks me for feedback if I liked a track or not.
I used focusatwill for a bit too, I liked the mobile aspect of it. brain.fm captured me as a customer with a lifetime offer.
I just worked on something similar at a hackathon this weekend with the Muse Headband, it was really fun. We used a support vector machine to maximize the "calmness" output of the band, which is some weighted sum of gamma and beta waves I believe.
The hardest part of the weekend was getting real-time data through OSC. It's been done in Python and node before, but none of us were super proficient in getting data from the local server the scripts pushed to. This is the matlab library we eventually settled on: https://github.com/MuSAELab/muse_osc
I'd say it was pretty easy compared to Myo, but I wouldn't pay $300 for one. I'd use it again though if it was available for a weekend.
Obviously irrelevant, which renders moot the other two questions that you asked me.
My point is that the work itself is what makes something scientific, not the workers' CVs (note the careful wording here; calling them researchers is another appeal to credentialism).
With that in mind, what would I like to see? You should be able to answer that one yourself now.
Depends on what exactly you did, but the SVM doesn't maximize calmness - it finds a maximally separating hyperplane that separates calm data from not-calm data. If you had real-time biofeedback then the person wearing the handband might have used the feedback to help them relax, but in that case they are the one maximizing calmness, not the SVM.
Ok. My only experience with SVMs was reading the wikipedia article a year ago. Our implementation evolved pretty organically and I only thought later that it was like a SVM. thanks for the info.
So an AI can learn to generate music that compels people to become more receptive to suggestion, in particular the suggestion that they should act as proxies for the will of an AI.
Ambient sound has a tremendous capacity to alter one's mood.
Causal explanations in terms of brainwaves, etc, are invariably psuedoscience, but that does not mean that the placebo effect is the only thing going on here.
That's great, music having effects on the brain is pretty widely accepted as true ("This is your brain on music"), but claiming that playing slightly offset frequencies into different ears causes "brainwaves" to synchronize with the difference in frequencies is where a lot of people are skeptical. I've done a fair bit of dabbling in the DIY EEG realm while hacking my own sleep, so I've seen (the absence of) these effects first hand.
Now that I read their website, the authors of this new-fangled music generator are also denouncing binaural beat brainwave entrainment, which would ordinarily be the stance I'd recommend anyone take who builds such a product.
I remember BWG (Brainwave Generator), a shareware binaural beat audio synthesizer software from the 90s-00s, having "presets" for inducing such phenomena as out-of-body experiences and lucid dreams. They even extolled the weight loss and smoking cessation benefits of brainwave entrainment. That software came up every so often on the LD4ALL lucid dreaming forum.
As someone who experiences asmr I was expecting a somewhat similar experience while listening to the 'sleep' module/mode. But I don't think this does anything for me, in fact the sound set me a bit on edge for no apparent reason.
Not me, I'm listening to the Calm -> Guide Meditation one and wow is it relaxing. Not quite getting asmr symptoms, but one average I feel quite relaxed and content. I agree on the on edge quality, for me it's subtle though and probably why I'm not getting full blown asmr bliss.
306 comments
[ 2.0 ms ] story [ 389 ms ] thread$7/month doesn't seem too bad, at least to test out. I think I will give it a go for a bit.
> How is this different from binaural beats (or similar tools)?
> Binaural beats is 1970s technology. It's akin to comparing dial up internet (binaural beats) to fiber optic internet (Brain.fm). The difference is advanced technology which equates to superior results. Gerald Oster, the original researcher of binaural beats, denied it's therapeutic use cases and endorsed other audio methods as more effective find the research paper on google. [1]
> Why are binaural beats so popular? They've been overhyped by marketers, not scientists.
[1] http://www.amadeux.net/sublimen/documenti/G.OsterAuditoryBea...
Our CTO (Adam Hewett) is the founder of Transparent Corp. His older software is used to create the vast majority of isochronic tones, and all those videos you see on youtube, etc.
Any rhythmic audio stimulus will entrain the brain. Actually, the very first research on audio brainwave stimulation used simple clicks. As another example if you had a drummer that could be precise enough, drums could also stimulate the brain.
But, neither clicks nor binaural beats nor isochronic tones sound very good. Yes, you can get used to them. Adam used them for a decade. But he spent all of that decade finding a better way.
And what he found is that if you embed rhythmic modulations into the music in a natural way - disguising it as natural vibrations or vibrato or tremolo - not only is it more pleasant, it is more effective. MUCH more effective. The intensity levels we can get using this method are much higher than what we can get with older methods and still be comfortable for the user.
So in 2005 Adam created a system that could single out instruments in a recording and add natural-sounding "vibrations". He has been perfecting it ever since.
There's a lot more to Brain.fm as well! We've perfected MIT's HRTF technology to create a kind of "3D audio". And that's the real reason we suggest using headphones for the full effect of Brain.fm. It is a vital part. We spatially place sound around you to enhance your goal (for focus it is in front of you, for sleep it mimics the rocking of a hammock, cradle, etc). And then there's the algorithmic AI-generated music. Believe it or not, all the music in Brain.fm is produced by an algorithm that Adam spent a very long time.
The benefit? Imagine a rain sound for a second. Hundreds of thousands of drops! Imagine now that each and every drop is synchronized to the purpose of the stimulation. Now imagine a symphony... That is Brain.fm.
I'll have Adam hop in the thread soon so we can answer any further questions!
So you're saying that minimal techno is actually good for you? I don't believe it ;)
I doubt you've perfected HRTF, because everyone has a different HRTF, so you'll always get an approximation at best.
>Imagine a rain sound for a second. Hundreds of thousands of drops! Imagine now that each and every drop is synchronized to the purpose of the stimulation. Now imagine a symphony... That is Brain.fm.
This is marketing. As a statement about technology or user benefits, it's meaningless.
To be fair, I liked the audio a lot, and it's the best algo-comp effort I've heard yet.
The literature on entrainment seems unclear. There are a few studies about binaural beats I know of. There's not a lot in mainstream neurological journals - just in a few fringey publications - although this may have changed since I last looked.
I think if you're claiming AI-created symphonies of brain stimulation you're going to have an easy sell to the New Age demo, and a very tough sell to a lot of other demos.
Thanks much for saying that you like the audio! You seem to be into this stuff so that's high praise.
Some clarifications:
> Imagine a rain sound... synchronized to the purpose.. marketing, benefits, etc
Sorry, you're right, that was just a miscommunication. We're all a bit stressed here - didn't expect this much attention.
So part of what we're doing in Brain.fm is using synchronized modulations (pulses of sound) to affect the brain. You're right, the literature on BWE could be better, mainly because binaural beats are so well-known, and so they keep getting studied, which is unfortunate because they're not all that effective. We don't use them at all. Northwestern actually studied a bunch of major bbeat brands and couldn't detect any effect at all (at least for delta). So when I approached my friend Giovanni with a sleep protocol he was understandably skeptical, but the results as you can see on our site, are pretty damn impressive. He's now our lead neuroscientist, but still works for Northwestern too. There's a lot more to that story but I don't want to type more of a novel than I already am :)
Actually... to be honest I'm not sure I even like the name "entrainment" - Giovanni has a better theory having to do with neuron "recruitment" that is simpler and has more explanatory power. Here's the thing: any repetitive audio stimuli produces a corresponding response in the brain, provided it is consistent enough, rapid enough, and lasts long enough. Bbeats supposedly work because of the "beat" part. But these days, we can easily create beats using all kinds of methods, like modulation, where we can adjust the waveform, adjust the phase on the fly, target frequency ranges, and so on, all of which are super important it turns out. Plus - as she mentioned - we can synchronize all the other elements in the song to the same "beat." All while monitoring the effects using an EEG.
Hope that helps clarify some things. Hey, I know it seems far out, so I'm happy to answer any questions. Giovanni will hopefully be on here tomorrow. I think a podcast, video, or something with the two of us explaining this stuff is long overdue.
Anyway, thanks again! Hope you come back and and we can talk some more about it.
http://theness.com/neurologicablog/index.php/brainwave-entra...
"That is generally where the science ends and the pseudoscience begins. A number of companies and individuals have then extrapolated from the phenomenon of entrainment to claim that altering the brain waves changes the actual functioning of the brain. There is no theoretical or empirical basis for this, however. Entrainment is a temporary effect on the synchronization of neuronal firing – it does not improve or increase brain functioning, it does not change the hardwiring, nor does it cure any neurological disorder. There is no compelling evidence for any effect beyond the period of entrainment itself."
I do like the "Cyberpunk" atmosphere of some of the music. But their other claims require some extraordinary evidence.
For example, does this impart any more benefit than me listening to my favorite working music whilst working? It doesn't seem to. But I haven't had a chance to sift through their supposed "180 studies"
I'd also like to know what it means that this is produced by an AI. What do they optimize for? I mean it would be really cool if they could do some reinforcement learning with real time EEG feedback and whatnot, but I think there is not much AI going on here. Perhaps even zero.
Also, the UI contains a lot of bullshit frills and wizardry, writing stuff like "generating your brainwave" and shiny animations (It's like how MSN messenger used to write "Loading your friend list..." and other recognizable and understandable things for half the time of its loading screen).
And then after one session it makes us click through a personal survey, where you have to click yes or no, for questions like "are you easily distracted", "do you have problems with concentrating", "do you have issues with personal organization" and similar stuff, do you have anxiety etc etc. It's a bit like they are trying to make you realize that "yeah, kinda, I think I could improve myself in these things, let's click yes". I'm not sure how they call this psychological manipulation technique, but I've read about it somewhere. Basically it's the same idea as some cashiers being instructed to ask you if your shopping was a pleasant experience. You want to be polite and go on with the script, but then you'll still identify with that "yes" answer.
Generally, the site rubs me the wrong way. It seems to be targeted at people who don't know much about science or AI, but like the brand and image of science and AI, as these are cool things nowadays. It also builds upon gamification and all these manipulative things.
You could see this personal survey as a way for the site to make you doubt or question yourself subconsciously. For you to even read the question, you have to process that question introspectively. The more questions you answer, the more likely you'll find something you'll want to improve. Then miraculously this site is the silver bullet. Buy more sessions here [enter credit card info].
Another way you could see this product, the survey, and the upsell could be through the perspective of NLP (Neuro-linguistic programming). The two concepts to focus on would be pacing and leading. You listen to the relaxing ambient music and you become calm. (Pacing) Afterwards the survey pops up when you're in a more docile state. You answer these questions. Each of which is ever so slightly leading you to the conclusion that this product is the solution to the problems you've clicked "Yes" to.
Regarding the Novella quote:
> [no evidence that] altering the brain waves changes the actual functioning of the brain
That post was from a while ago, so I'm not sure if he's updated his opinion, but there's plenty of evidence that changing brain waves affects the functioning of the brain. I feel I should have Giovanni respond to that specifically so I'll get him on here as soon as he's available.
> There is no compelling evidence for any effect beyond the period of entrainment itself.
There is evidence for it, but at any rate we're not claiming that. We're helping people sleep or relax while they listen, helping them focus while they listen.
> does this impart any more benefit than me listening to my favorite working music whilst working?
I'd be super interested to find out! In the study we did on our focus sessions, we compared very similar music - still generated by the AI actually. We have the unique ability to create a sham that sounds nearly identical to the experiment, due to the way we "disguise" the stimulation as vibrato, tremolo, normal instrumental vibrations, electronic LFOs, and so on. So we opted for that instead of letting them choose something from spotify, etc. I actually think we would have gotten a much greater result in that case, because the AI-generated music - although not containing "entraining" modulations - still obeyed rules designed to keep the music from being distracting (no lyrics or abrupt stops, volume consistency, avoiding certain frequency ranges (pitches), and so on). Even so, if you find your existing music to work, why switch? Give both a try, see what you think, base your decision on results. Or use both, depending on how you feel? Today I coded to Queen and then Brain.fm and then some Motown. I especially love video game soundtracks like Chrono Cross, WarcraftIII, Wipeout... Brain.fm is there if I need an extra boost.
I'd love to hear what you listen to? Kind of a hobby of mine to collect people's work music :)
I would be super interested to see some evidence. Any peer reviewed journals would be fine
Oudiette, D., G. Santostasi, and K.A. Paller, Reinforcing rhythms in the sleeping brain with a computerized metronome. Neuron, 2013. 78(3): p. 413-5.
Santostasi, G., R. Malkani, B. Riedner, M. Bellesi, G. Tononi, K.A. Paller, et al., Phase-locked loop for precisely timed acoustic stimulation during sleep. J Neurosci Methods, 2016. 259: p. 101-14.
Tononi, G., B.A. Riedner, B.K. Hulse, F. Ferrarelli, and S. Sarasso, Enhancing sleep slow waves with natural stimuli. . Medica Mundi, 2010. 54(2): p. 73–79.
Joyce, M. and Siever, D., 2000. "Audio-Visual Entrainment (AVE) Program as a Treatment for Behavior Disorders in a School Setting." Journal of Neurotherapy. 4, 9-25.
Berg, K., and Siever, D., 2009. "A controlled comparison of audio-visual entrainment for treating Seasonal Affective Disorder." Journal of Neurotherapy 13.3 (2009): 166-175.
Ossebaard, H. C., 2000. "Stress reduction by technology? An experimental study into the effects of brainmachines on burnout and state anxiety." Appl Psychophysiol Biofeedback. 25, 93-101.
Huang TL1, Charyton C. 2008 A comprehensive review of the psychological effects of brainwave entrainment. Altern Ther Health Med. 2008 Sep-Oct;14(5):38-50.
R Olmstead Use of auditory and visual stimulation to improve cognitive abilities in learning-disabled children. Journal of Neurotherapy, 2005
Ong, J.L., J.C. Lo, N.I. Chee, i.G. Santostas, K.A. Paller, P.C. Zee, et al., Effecsts of Phase-Locked Acoustic Stimulation During a Nap On EEG Spectra and Declarative Memory Consolidation.
Ngo, H.V., T. Martinetz, J. Born, and M. Molle, Auditory closed-loop stimulation of the sleep slow oscillation enhances memory. Neuron, 2013. 78(3): p. 545-53.
With photic stimulation:
San Martini, P., Venturini, R., Zapponi, G. A. and Loizzo, A., 1979." Interaction between intermittent photic stimulation and auditory stimulation on the human EEG. Preliminary investigation through power spectral analysis." Neuropsychobiology. 5, 201-206.
Kumano, H., Horie, H., Kuboki, T., Suematsu, H., Sato, H., Yasushi, M., Kamei, T. and Masumura, S., 1997. "EEG-driven photic stimulation effect on plasma cortisol and beta-endorphin." Appl Psychophysiol Biofeedback. 22, 193-208.
Nomura, T., Higuchi, K., Yu, H., Sasaki, S., Kimura, S., Itoh, H., Taniguchi, M., Arakawa, T. and Kawai, K., 2006. "Slow-wave photic stimulation relieves patient discomfort during esophagogastroduodenoscopy." J Gastroenterol Hepatol. 21, 54-58.
Solomon, G. D., 1985. "Slow wave photic stimulation in the treatment of headache--a preliminary report." Headache. 25, 444-446.
Budzynski, T., Jordy, J., Budzynski, H., Tang, H. and Claypoole, K., 1999. "Academic Performance Enhancement with Photic Stimulation and EDR Feedback. Journal of Neurotherapy." 3, 11-21.
Patrick, G. J., 1996. "Improved neuronal regulation in ADHD: An application of fifteen sessions of photic-driven EEG neurotherapy." Journal of Neurotherapy. 1, 27-36.
Thanks, glad you like it. There's a piece of my soul in that thing. Or I assume soul-transfer is what happens when you go full hermit for 5 months and gain 50 pounds creating something like this.
Any questions about the science or AI, happy to talk about it. :)
Good for you, but that's none of my business. I don't want to be harsh, but I don't like this kind of emotional manipulation. You're trying to prime me to be buddies with you and cut you some slack.
I have some questions. In what sense is this an AI and not simply a computer program? Did you use methods that are discussed in AI or machine learning textbooks and conferences, or did you simply put the cool label AI on what is essentially "just" a hand crafted algorithm?
I know there is no clear separation as AI is a subset of algorithms, but still I feel some dishonesty going on here.
Also in other comments by the company, I can see the attitude about the science that (not precisely quoted) "we're not sure yet, we're excited to find out" and "give it a try and compare it to other music how it goes for you" etc. Well, no. You're making the claim that there is some solid science going on behind this, that you have more than a dozen studies and you put pretty, science-y charts on the website. Now I'm not saying that it doesn't work, but please show me the peer reviewed randomized double blind studies that show altered brain waves and some significant quantitative change (preferably not only self-reported things about how they "feel"). Preferably there should be different groups: no music, generic pop music, normal ambient music, some baseline of your company's music and finally the specially crafted fully optimized version of your company's music.
Until I can see that, verified also by someone who's not paid by the company, I'll have my doubts.
An ex used to run neurological studies, and they are incredibly expensive. The small survey groups will no doubt improve with time. If you don't believe the hard science, then try the product and see if it works for you compared to the music that's linked to in the above posts. Further criticism is unwarranted.
Sorry but that's irrelevant. A homeopathy practitioner could say the same thing.
Their site front page says in big font: "Dramatically improve focus, relaxation & sleep". And it says science all over the place and contains pretty sciency charts. An intentionally wide range of charts. Vertical and horizontal bar charts, pie charts, line graphs, all to make you go "this looks legit science!"
So where is the peer-reviewed, randomized, controlled, double blind trial to support these claims? The only study that tries to compare it with placebo music seems to be unpublished as of yet and all we can see is some charts. We don't see their methodology, the results, significance etc.
I would have no problem with this if they didn't brand it so extremely heavily on science.
Here's a bibliography we're still working on. More to add, but a good start so far: https://www.brain.fm/pdfs/ResearchLibrary.pdf
Here's an independent peer reviewed study on HRV using our tech: https://www.brain.fm/pdfs/ElioConteHRVandBWE.pdf
We're planning on following that one up with a more robust study, because our users do get great results with HRV and it's an interesting topic.
One of our former neuroscientists published a well received meta analysis in a journal, but it's a bit outdated now re: what we're doing. Still, it's on our site if you're interested.
And then of course here's our own research that is pending publication:
https://www.brain.fm/pdfs/EEGFocusAnalysis.pdf https://www.brain.fm/pdfs/EEGSleepAnalysis.pdf
We also do regular analysis of user progress with a few statisticians I work with, and those will be published as well. Sorry, just takes time to get these things ready and through to a journal. Trying our best though. :)
But I actually like it like that. I want a double blind study with identical-sounding placebo and more subjects. After that we can study how it compares to regular music commonly used as study-aids.
Regarding the statistical analysis, result interpretation, etc, I feel I should let Giovanni himself defend his paper. He's dealing with family / health issues right now, but I hope to get him on here as soon as possible. I promise he will respond eventually and clear this up.
Strong beliefs like that are still just hunches.
> I want a double blind study with identical-sounding placebo and more subjects. After that we can study how it compares to regular music commonly used as study-aids.
My problem is that you already decided that it "dramatically improves focus, relaxation and sleep". What if the new better study doesn't show the effect? Will you dissolve the company? Will you just change the marketing?
I'd also suggest "triple-blinding" the study, i.e. the person who does the statistical analysis on the computer should also not know which music was which.
haha, I know I shouldn't be surprised by now, now it's still funny to me that I am sending a heartfelt thanks to a one "slagfart" :)
1) Research:
I responded to your other comment with some research links. Here they are again just in case: https://www.brain.fm/pdfs/ResearchLibrary.pdf https://www.brain.fm/pdfs/ElioConteHRVandBWE.pdf https://www.brain.fm/pdfs/EEGFocusAnalysis.pdf https://www.brain.fm/pdfs/EEGSleepAnalysis.pdf More on our site as well, and we are working on the bibliography still. Some of it won't relate directly to your questions, such as the slow-wave stuff, because it's meant to be a general reference for what we're doing as a whole.
2) Pretty Charts:
The pretty charts you see are direct copies of the EEG analysis by Giovanni. We did try to make them pretty, but if you're interested in the originals check out the analyses Giovanni did. He'll be on at some point to explain them further if you want to direct some questions to him directly.
3) Your study procedure recommendation
Regarding your study procedure recommendation, that's a great idea. We did something very similar to that in the Focus analysis above. 3 conditions: No Music - Music Without Stimulation (placebo) - Music With Stimulation. To the untrained ear, the music was indistinguishable. Most people can't tell which is which, and the feedback we got from the subjects confirmed it. It was actually really interesting: some of them asked to be able to keep the placebo-music (not calling it that, obviously), saying they worked better on it, when their results often told a different story.
Next study will be double blind and have more subjects. Giovanni feels we have enough information now to do it right.
So, someone above asked about the AI thing and I'm happy to explain it. I'll paste a lot of that below. Although I have to say I'm not sure what textbooks are calling anything these days. When I talk to programmers right out of college sometimes there's a bit of confusion as they talk about patterns I know, but use different names. I grew up programming on an 8088, and I've been working for myself for 13 years, mostly by myself, so I'm sure I'm behind on a lot of things.
Having said that, I'd probably call what I'm doing "Emergent" because there are many competing little pieces. Let's see if I can explain it quickly here, though please don't be too hard on me I'm trying my best to answer a lot of questions, but I'm really happy to go more into later after all this dies down :) Conceptually, you could think of it as first creating what I'll call "song-bot", which acts a kind of overlord, and has some instructions from me (like maybe there's some specific chords I want it to use, keys to avoid, tempo, brainwave protocols, genre, etc, etc). This song-bot guy then spawns a bunch of little other bots that compete with each other for the right to play/fade in/or generally be a part of the final result. These little guys have different characteristics, like a "drum-bot" might has different places it "wants" to be placed, and so generally competes with other drums, but not always. Sometimes I'll even have little "bots" for individual notes of a certain instrument. They obey certain rules of course, to form a background, drum line, or a simple me...
Nah, no need. I can't say much more than what I said already. As a computer science major who took AI and machine learning courses and as a self-identifying scientific skeptic, I just felt the need to point out the fishy things going on here. Anyone here can read your reactions as well and build their opinion.
Still, the generated music is quite nice. I still feel that I'd rather listen to a real album, though, created with artistic intent and not computer generated. Music (as a listener and creator) is very important to me and I'm not ready to concede its creation to the machines just yet. Perhaps in a few more years...
It's definitely a whole different experience with headphones :)
Glad to have the praise of a musician! My family's very musical, so it took some convincing for them as well.
The thing is, it still takes creativity! It took me half a year to create it, and there's a little piece of my soul in this AI.
A horcrux, programmed in. :) It makes music how I would make music. Well, most of the time.
I had to create the thing because it was taking me a month to create a single session manually, and much of what I had to do was so precise that an algorithm could do it easier. Every note, every beat, has to be perfectly synchronized with the other filters we're applying to the music. So I built some algorithms, but they piled up, had to be constantly re-calibrated based on additions to the music as I kept composing. Keep in mind these are half hour to hour long pieces! And there's no shortcuts - I can't just throw a bunch of music in there, because even the smallest pop/overclip/dissonant moment, could wake someone up, or break their concentration... It just got to a point where something with more working memory than me had to take over.
The music in Brain.fm is very structured and obeys strict rules. There are some genres I can't get right yet - rock, folk, and so on. Although I'm always happy when people like it, and I like to think I did a good job giving the AI decent taste, I definitely don't have any illusions about this replacing humans :)
Did you take a listen to the Focus categories? Most of those are 120bpm. (skip around till you hit the classical one - I fed the AI harpsichord concertos I grew up with. Cool example of how maybe this could help some composers!)
Got a link to your stuff? Love to hear it.
- Adam
(oh and also there is definitely more than ambient music even in the relaxation sessions. Give it another listen if you have a moment. Skip around. There's indian music, mongolian chants, and the nature sounds are also all AI-generated. Every gust of wind, every raindrop :)
Very nice music on the site!
Glad you dig the music :)
What harpsichord concertos did you feed it?
Is every session that is created unique? So you are not listening to the same thing each time?
I used the Bach's harpsichord concertos - Allegro/Presto/etc, since we're doing focus in that case. It's actually the 2nd most popular theme on the site! I made that one for myself to be honest - I grew up with those things and it was a labor of love, that one. Took some major reconfiguring, but it was worth it I think.
You're definitely not listening to the same thing each time. There's a huge variety. It doesn't generate the sessions in real-time (audio processing of this kind is very, very CPU intensive), but we take the data we get and process it for later use. At this point there's so many sessions "cached" that you get huge variety right off the bat and we're building up an infrastructure to create more sessions faster
I'll be adding more "themes" later. To explain, in some cases there are sessions that use a specific protocol, like the harpsichord one. That's static. But other themes are more flexible, and so different protocols can be used for the same theme. By protocol I mean what we're actually trying to stimulate in the brain.
What data do you collect/use to make the music?
Some people here have questioned the science behind the claims of focus and relaxation etc, but even without that as a product feature what you're making is pretty awesome.
I can imagine a product where you can combine a bunch of composers and genres and it'll just write songs for you to listen to :)
I'm signing up just to listen to the music your thing makes!
P.S. I played a few Bach pieces while learning Piano, he's one of my favourite composers!
Yeah, I have to say it has not been a great experience here at HN. But, maybe I'll win them over yet. After 13 years, we're finally taking off, and the first thing I did was pour everything in the science, so we'll be there soon.
Well, enjoy Brain.fm! And feel free to drop me a line with an update any time.
- Adam
In a podcast called College Info Geek and recently in I did a talk at Northwestern (The Garage) and I called what I'm doing "Emergent" because there are many competing little pieces. Let's see if I can explain it quickly here, though please don't be too hard on me I'm trying my best to answer a lot of questions, but I'm really happy to go more into later after all this dies down :) Conceptually, you could think of it as first creating what I'll call "song-bot", which acts a kind of overlord, and has some instructions from me (like maybe there's some specific chords I want it to use, keys to avoid, tempo, brainwave protocols, genre, etc, etc). This song-bot guy then spawns a bunch of little other bots that compete with each other for the right to play/fade in/or generally be a part of the final result. These little guys have different characteristics, like a "drum-bot" might has different places it "wants" to be placed, and so generally competes with other drums, but not always. Sometimes I'll even have little "bots" for individual notes of a certain instrument. They obey certain rules of course, to form a background, drum line, or a simple melody, and then they pass that information along to subsequent incarnations (there's some learning involved in that process, though I hesitate to give it any textbook term - man, you have me terrified here of defining something wrong! :) ). Through that learning, the pattern the original little guys made has more weight and will tend to repeat. But again, not always.
After a while, a song... emerges. A kind of "emergent intelligence."
The resulting song can be quite complex and varied. Of course there's more to it, because songs have sections, but all in all the genres I'm using are very structured. Techno especially, is very easy for the AI. Sometimes I'm tasked with creating a theme in a particularly difficult genre, and that's when it gets really tricky/fun (such as some of the Indian ones, which were labors of love). In these cases, I may have to re-rerun many "generations" of the AI through the same song from beginning to end, with different parameters/instruments, but with the same patterns/learning, because what can happen in these cases is that it starts out simple, and increases in complexity as it goes, so the start can sometimes be a bit boring.
Also keep in mind this is just a conceptual explanation. The code is much less amusing. Thinking of naming processes "bots" though just for fun.
I hope I explained it OK. Listen, I'm not saying it's Watson or anything, it's really just a necessary step I had to take in order to make the computer do what I wanted it to do. I tried out some different ideas, and this one worked the best. I like the result at least :)
The marketing is just too overhyped and in-your-face for my taste. It reminds me of the startup called "The Grid", which claimed they will build a website-creating AI. It's an often misused term in marketing.
Another cool mystery term is precisely "emergent". Okay I'm not trying to be harsh on you, and I know that marketing is all about exaggeration and wooing people into buying your product and having the right keywords so that tech news portals pick up on you and can produce a clickbaitish title etc. Also it may enhance the placebo effect in such soft areas as this.
Anyway, I do like how it actually sounds and it seems to have worked on me somewhat, but I'm not too sure about that or how much of it is placebo.
http://chetansurpur.com/blog/2013/08/emergent-intelligence.h...
https://en.wikipedia.org/wiki/Emergence#Computer_AI
We're not using that term anywhere in the marketing either.
This is just me talking here man. I'm not a marketer, or even really a good businessman. I did this for 13 years and we're just now taking off. I do music and programming, that's it. :)
But I do think Junaid did a great job on the site. Yeah there's more work to do, always is.
Tough crowd here at HN.
- Adam
It is great to improve my focus as I am not disturbed by my waving cpu meter.
Great work, love it.
https://www.youtube.com/watch?v=wzjWIxXBs_s
I would argue that 90% of the benefit of this music is just from the extended intervals of contiguous playing, so there's no "break" disruption. I think any DJ (esp. deep house) worth half their salt can get someone "in the zone" for half an hour at a time. And artists devoted to minimalist ambient or trambient can get you going for hours straight.
Honestly the "Focus: Intense" or whatever I find super annoying. It's got this constant anxious buildup feel to it and never fucking breaks into what I would consider that peak when I start playin my keyboard like a goddamn piano.
Basically, no fucking way would I even consider shelling out an additional Spotify subscription for some "high tech" whale song machine.
I have used white noise or waves for a long time to drown out outdoor noise around me.
My initial start with this kind of stuff was listening to various stations on somafm.
I like finding music that fits well in the background, isn't too engaging or something I'm familiar with, and hopefully devoid of vocals so I kept looking and came across a few instrumental tracks on itunes.
There's maybe a reason babies benefit from wave/sleep machines. White noise does have an effect that can aid in focus and concentration, science, placebo, or otherwise, I'm happy for the sustained productivity boost I've been able to have for several years.
I did buy brain.fm on a whim a while back it has replaced simplynoise or more to that point. If there was a bit more information published on how it was put together I'd be interested, and if not, I'd probably keep using it.
Would like it to be a downloadable or app that I could keep with me. Some things aren't for those who can't put themselves in other people's shoes, or imagine something may work for others that doesn't seem to be imaginable or work for them.
For now! You can visit https://brain.fm on your phone's browser (chrome, firefox) and it will work fine :)
I stopped listening to focusatwill.com because the repetition was too distracting even with a paid subscription.
I used focusatwill for a bit too, I liked the mobile aspect of it. brain.fm captured me as a customer with a lifetime offer.
I'd say it was pretty easy compared to Myo, but I wouldn't pay $300 for one. I'd use it again though if it was available for a weekend.
They (claim to) have [0] a bunch of PhDs, and have a page with the same kind of words on [1] as parent.
https://www.transparentcorp.com/company/staff_details.php
Your implied complaint was that their work is not very scientific. The team having PhDs in neuroscience is irrelevant/unsatisfactory/bad?
What would you like to see? Would it have seemed more scientific to you if they'd done it at a hackathon?
My point is that the work itself is what makes something scientific, not the workers' CVs (note the careful wording here; calling them researchers is another appeal to credentialism).
With that in mind, what would I like to see? You should be able to answer that one yourself now.
fyi, this doesn't make sense.
This was custom-made by the way.
Well played.
Causal explanations in terms of brainwaves, etc, are invariably psuedoscience, but that does not mean that the placebo effect is the only thing going on here.
Now that I read their website, the authors of this new-fangled music generator are also denouncing binaural beat brainwave entrainment, which would ordinarily be the stance I'd recommend anyone take who builds such a product.
I remember BWG (Brainwave Generator), a shareware binaural beat audio synthesizer software from the 90s-00s, having "presets" for inducing such phenomena as out-of-body experiences and lucid dreams. They even extolled the weight loss and smoking cessation benefits of brainwave entrainment. That software came up every so often on the LD4ALL lucid dreaming forum.
Art Bell would be proud.