Currently, there are no participants in our dataset with >100hrs -- intentionally so, we've been optimizing heavily for diversity of dataset up to this point. We've explored the idea of fine tuning on a particular…
Yeah -- we have the participants use chinrests as well, which reduces head motion artifacts for typing but less so for speaking (because they have to move their heads for that of course). so a lot of the data is with…
hahahah tell me about it!
Yeah I think the way we trained the embedding model focused a lot on how to make it as efficient as possible, since it is such a data-limited regime. So I think based on (early) scaling results, it'll be closer to…
1. The predictions get better with more data - and we don't seem to be anywhere near diminishing returns. 2. The thing we care about is generalization between people. For this, less data from more people is much better.
EEG has very good temporal resolution, but quite bad spacial resolution, and other modalities have different tradeoffs
The second most useful by far is Indeed, where we post an internship opportunity for participants interested in doing 10 sessions over 10 weeks. Other things that work pretty well are asking professors to send out…
Hey I'm Nick, and I originally came to Conduit as a data participant! After my session, I started asking questions about the setup to the people working there, and apparently I asked good questions, so they hired me.…
Currently, there are no participants in our dataset with >100hrs -- intentionally so, we've been optimizing heavily for diversity of dataset up to this point. We've explored the idea of fine tuning on a particular…
Yeah -- we have the participants use chinrests as well, which reduces head motion artifacts for typing but less so for speaking (because they have to move their heads for that of course). so a lot of the data is with…
hahahah tell me about it!
Yeah I think the way we trained the embedding model focused a lot on how to make it as efficient as possible, since it is such a data-limited regime. So I think based on (early) scaling results, it'll be closer to…
1. The predictions get better with more data - and we don't seem to be anywhere near diminishing returns. 2. The thing we care about is generalization between people. For this, less data from more people is much better.
EEG has very good temporal resolution, but quite bad spacial resolution, and other modalities have different tradeoffs
The second most useful by far is Indeed, where we post an internship opportunity for participants interested in doing 10 sessions over 10 weeks. Other things that work pretty well are asking professors to send out…
Hey I'm Nick, and I originally came to Conduit as a data participant! After my session, I started asking questions about the setup to the people working there, and apparently I asked good questions, so they hired me.…