Which can be changed at any time.
More realistically: just import it from the rest of the world.
Supply generates its own demand; by making captioning even cheaper, it can increase the demand for transcription services and people to check it over. There are a lot of podcasts and YT videos that could benefit from…
We have to hardwire architectures because we can't learn architectures yet, or to put it another way, backpropagation doesn't yet work on hyperparameters as well as on parameters. Hyperparameters should be learnable as…
If you want fine-grained tagging/categorization, you would be even better off with the -boorus.
That was deliberate. I couldn't resist either.
It could also reflect what is most distinguishable. Which is easier for a NN to confidently distinguish: black pubic hair on black skin, or black pubic hair on white skin? Darker nipples on black skin, or darker nipples…
> (He's at George Mason University, which is a right-wing think tank, and has to say stuff like that to get tenure.) Hanson was an extreme libertarian long before he got tenure or joined GMU, or even before he invented…
I remember the one you're talking about: http://fusion.net/story/244545/famous-and-broke-on-youtube-i... (first hit for 'Youtube star waitressing')
Everywhere else on the Internet?
What sort of performance can be expected compared to running in the terminal? How large NNs will this scale to in practice? I see a 50-layer resnet is mentioned; but not 1000-layers?
It's interesting to read about the debate between doing editing/screen-drawing on the physical terminal ('smart' hardware) and doing it all in software. The wheel of reincarnation in action! Something we've seen in tech…
How would you know if they have been? As the human population shoots up massively, car-miles have increased enormously over the past century, and rural areas become denser, the number of deer-car accidents would…
The obsession with information theory here seems like a classic nail-hammer thing. The number of bits my tests convey is totally useless to think about and certainly not worth spending pages on. All I want from my tests…
This is perhaps the stupidest and most hysterical thing I've ever read on Stross's blog. I don't think I need to explain why Brexit is not going to lead to the https://en.wikipedia.org/wiki/European_Potato_Failure and a…
You can definitely see where this is going. My first thought was the same: 'we need eyetracking for foveated rendering anyway, so we can get realistic eyes for free', and if you can do that, you can track the eyebrows…
I wouldn't bet a bent penny on it: "Experts said it was likely that the NSA or FBI had approached other Internet companies with the same demand, since they evidently did not know what email accounts were being used by…
> If you think the Internet is as safe and controlled as a shopping mall, you probably should be reading Krebs on Security more. That's an amusing comparison, given how much of Krebs focuses on offline ATM skimming,…
You could probably apply the same code. The dataset ("acquire 75,471 sketches of 12,500 objects") sounds adequate, and if not, can be boosted by first training a CNN to do photo->sketch (throwing away information is…
It doesn't seem to lead to any harms when done as part of preimplantation genetic diagnosis in general, so this specific case shouldn't be too bad.
You're not supposed to. Image generation and modeling scene dynamics is a hard task, and thumbnail scale is what we're at at the moment. Nevertheless, those and other papers do demonstrate that NNs are perfectly capable…
> All of those goals are achieved with its design and improving on this foundation is certainly possible. These were all hard problems to solve at the time, given the state of the art was CVS, subversion and perforce.…
Note the moving objects in those generated/predicted thumbnails.
> Neural networks are good at adaptation, but useless at forming concepts about how the data is structured. For example: in video we do motion compensation, because we know video captures motion since objects move in…
Many NNs can be compressed considerably without losing much performance. The runtime of RNNs is more concerning, as is whether anyone wants to move to a new image format, but it's still interesting pure research in…
Which can be changed at any time.
More realistically: just import it from the rest of the world.
Supply generates its own demand; by making captioning even cheaper, it can increase the demand for transcription services and people to check it over. There are a lot of podcasts and YT videos that could benefit from…
We have to hardwire architectures because we can't learn architectures yet, or to put it another way, backpropagation doesn't yet work on hyperparameters as well as on parameters. Hyperparameters should be learnable as…
If you want fine-grained tagging/categorization, you would be even better off with the -boorus.
That was deliberate. I couldn't resist either.
It could also reflect what is most distinguishable. Which is easier for a NN to confidently distinguish: black pubic hair on black skin, or black pubic hair on white skin? Darker nipples on black skin, or darker nipples…
> (He's at George Mason University, which is a right-wing think tank, and has to say stuff like that to get tenure.) Hanson was an extreme libertarian long before he got tenure or joined GMU, or even before he invented…
I remember the one you're talking about: http://fusion.net/story/244545/famous-and-broke-on-youtube-i... (first hit for 'Youtube star waitressing')
Everywhere else on the Internet?
What sort of performance can be expected compared to running in the terminal? How large NNs will this scale to in practice? I see a 50-layer resnet is mentioned; but not 1000-layers?
It's interesting to read about the debate between doing editing/screen-drawing on the physical terminal ('smart' hardware) and doing it all in software. The wheel of reincarnation in action! Something we've seen in tech…
How would you know if they have been? As the human population shoots up massively, car-miles have increased enormously over the past century, and rural areas become denser, the number of deer-car accidents would…
The obsession with information theory here seems like a classic nail-hammer thing. The number of bits my tests convey is totally useless to think about and certainly not worth spending pages on. All I want from my tests…
This is perhaps the stupidest and most hysterical thing I've ever read on Stross's blog. I don't think I need to explain why Brexit is not going to lead to the https://en.wikipedia.org/wiki/European_Potato_Failure and a…
You can definitely see where this is going. My first thought was the same: 'we need eyetracking for foveated rendering anyway, so we can get realistic eyes for free', and if you can do that, you can track the eyebrows…
I wouldn't bet a bent penny on it: "Experts said it was likely that the NSA or FBI had approached other Internet companies with the same demand, since they evidently did not know what email accounts were being used by…
> If you think the Internet is as safe and controlled as a shopping mall, you probably should be reading Krebs on Security more. That's an amusing comparison, given how much of Krebs focuses on offline ATM skimming,…
You could probably apply the same code. The dataset ("acquire 75,471 sketches of 12,500 objects") sounds adequate, and if not, can be boosted by first training a CNN to do photo->sketch (throwing away information is…
It doesn't seem to lead to any harms when done as part of preimplantation genetic diagnosis in general, so this specific case shouldn't be too bad.
You're not supposed to. Image generation and modeling scene dynamics is a hard task, and thumbnail scale is what we're at at the moment. Nevertheless, those and other papers do demonstrate that NNs are perfectly capable…
> All of those goals are achieved with its design and improving on this foundation is certainly possible. These were all hard problems to solve at the time, given the state of the art was CVS, subversion and perforce.…
Note the moving objects in those generated/predicted thumbnails.
> Neural networks are good at adaptation, but useless at forming concepts about how the data is structured. For example: in video we do motion compensation, because we know video captures motion since objects move in…
Many NNs can be compressed considerably without losing much performance. The runtime of RNNs is more concerning, as is whether anyone wants to move to a new image format, but it's still interesting pure research in…