Speaker unverified: evaluation

Transcript context

…So can you just adjust to the baseline to make it relative to the baseline nonstop? Yeah, this is a great question. So with monkeys, we have found various ways to do this. One example way to do this is you ask them to do some behavioral tasks like play the game with a joystick, you measure what’s going on in the brain. You compute some mean of what’s going on across all the input features, and you subtract that on the input when you’re doing your BCI session, works super well. For whatever reason, that doesn’t work super well with Noland. I actually don’t know the full reason why, but I can imagine several explanations. One such explanation could be that the context effect difference between some open-loop task and some closed-loop task is much more significant with Noland than it is with the monkey. Maybe in this open-loop task, he’s watching the Lex Fridman Podcast while he’s doing the task or he’s whistling and listening to music and talking with his friend and ask his mom what’s for dinner while he’s doing this task. So the exact difference in context between those two states may be much larger and thus lead to a bigger generalization gap between the features that you’re normalizing at open-loop time and what you’re trying to use at closed-loop time. That’s interesting. Just on that point, it’s incredible to watch Noland be able to multitask, to do multiple tasks at the same time, to be able to move the mouse cursor effectively while talking and while being nervous because he’s talking in front of [inaudible 06:33:45]…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.