Speaker unverified: belief

Transcript context

…Yeah. Maybe I’ll take one zoom out step there, which is just explaining why we care to measure this at all. So again, our goal is to provide the user the ability to control the computer as well as I can, and hopefully better. And that means that they can do it at the same speed as what I can do, it means that they have access to all the same functionality that I have, including all those little details like command tab, command space, all this stuff, they need to be able to do it with their brain, and with the same level of reliability as what I can do with my muscles. And that’s a high bar, and so we intend to measure and quantify every aspect of that to understand how we’re progressing towards that goal. There’s many ways to measure BPS by the way, this isn’t the only way, but we present the user a grid of targets, and basically we compute a score which is dependent on how fast and accurate they can select, and then how small are the targets. And the more targets that are on the screen, the smaller they are, the more information you present per click. And so if you think about it from information theory point of view, you can communicate across different information theoretic channels, and one such channel is a typing interface, you can imagine, that’s built out of a grid, just like a software keyboard on the screen. And bits per second is a measure that’s computed by taking the log of the number of targets on the screen. You can subtract one if you care to model a keyboard, because you have to subtract one for the delete key on the keyboard. But log of the number of targets on the screen, times the number of correct selections, minus incorrect, divided by some time window, for example, 60 seconds. And that’s sort of the standard way to measure a cursor control task in academia. And all credit in the world goes to this great professor, Dr. Shenoy of Stanford who came up with that task, and he’s also one of my inspirations for being in the field. So all the credit in the world to him for coming up with a standardized metric to facilitate this kind of bragging rights that we have now to say that Noland is the best in the world at this task with this BCI. It’s very important for progress that you have standardized metrics that people can compare across. Different techniques and approaches, how well does this do? So big kudos to him and to all the team at Stanford. portant for progress that you have standardized metrics that people can compare across. Different techniques and approaches, how well does this do? So big kudos to him and to all the team at Stanford. Yeah, so for Noland, and for me playing this task, there’s also different modes that you can configure this task. So the Webgrid task can be presented as just sort of a left click on the screen, or you could have targets that you just dwell over, or you could have targets that you left, right click on, you could have targets that are left, right click, middle click, scrolling, clicking and dragging. You can do all sorts of things within this general framework, but the simplest, purest form is just blue targets show up on the screen, blue means left click. That’s the simplest form of the game. And the sort of prior records here in academic work and at Neuralink internally with NHPs have all been matched or beaten by Noland with his Neuralink device. So prior to Neuralink, the world record for a human using device is somewhere between 4.2 to 4.6 BPS, depending on exactly what paper you read and how you interpret it. Noland’s current record is 8.5 BPS. and again, this sort of median Neuralinker performance is 10 BPS. So you can think of it roughly as, he’s 85% the level of control of a median Neuralinker using their cursor to select blue targets on the screen. I think there’s a very interesting journey ahead to get us to that same level of 10 BPS performance. It’s not the case that the tricks that got us from 4 to 6 BPS, and then 6 to 8 BPS are going to be the ones that get us from 8 to 10. And in my view, the core challenge here is really the labeling problem. It’s how do you understand, at a very, very fine resolution, what the user’s attempting to do? And I highly encourage folks in academia to work on this problem. What’s the journey with Noland on that quest of increasing the BPS on Webgrid? In March, you said that he selected 89,285 targets in Webgrid. So he loves this game, he’s really serious about improving his performance in this game. So what is that journey of trying to figure out how to improve that performance? How much can that be done on the decoding side? How much can that be done on the calibration side? How much can that be done on the Noland side of figuring out how to convey his intention more cleanly?…

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