Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

BrainGPT turns thoughts into text

iflscience.com

Post reply on HN
Print view View original

141–150 of 208 posts

Re: BrainGPT turns thoughts into text

#141

Post by IshKebab »

drzzhan wrote: post #138
mikpanko wrote: post #136

I did a PhD in brain-computer interfaces, including EEG and implanted electrodes. BCI research to a big extent focuses on helping paralyzed individuals regain communication. Unfortunately, EEG doesn’t provide sufficient signal-to-noise ratio to support good communication speeds outside of the lab with Faraday cages and days/weeks of de-noising including removing eye-movement artifacts in the recordings. This is a phy…

What is it noise-to-signal ratio? Sorry I don't know much about the field but that sounds like something can shutdown ideas like "we can put eeg into transformer and it will work". So may I ask what reference papers that I need to know on this?

Signal to noise ratio is a very basic thing; you can Google it.

Re: BrainGPT turns thoughts into text

#142

Post by southerntofu »

drzzhan wrote: post #138
mikpanko wrote: post #136

I did a PhD in brain-computer interfaces, including EEG and implanted electrodes. BCI research to a big extent focuses on helping paralyzed individuals regain communication. Unfortunately, EEG doesn’t provide sufficient signal-to-noise ratio to support good communication speeds outside of the lab with Faraday cages and days/weeks of de-noising including removing eye-movement artifacts in the recordings. This is a phy…

What is it noise-to-signal ratio? Sorry I don't know much about the field but that sounds like something can shutdown ideas like "we can put eeg into transformer and it will work". So may I ask what reference papers that I need to know on this?

Not from that field, but "reading" the brain means electromagnetism. In real life, EM interference is everywhere from lights, electric devices, cellphone towers... EVERYWHERE. Parent meant brain waves are weak to detect compared to all surrounding interference, except when a lab faraday cage blocks outside interference then the brain becomes "loud" enough to be read.

https://en.wikipedia.org/wiki/Signal-to-noise_ratio

https://en.wikipedia.org/wiki/Faraday_cage

Re: BrainGPT turns thoughts into text

#143

Post by ghayes »

chpatrick wrote: post #137
mike_hearn wrote: post #117

Earlier quoted context omitted.

Urgh. And it gets worse from there. The bugs list on the repo has a closed and locked bug report from someone claiming that their code is using teacher forcing! https://github.com/duanyiqun/DeWave/issues/1 In a normal recurrent neural network, the model predicts token-at-a-time. It predicts a token, and that token is appended to the total prediction so far which is then fed back into the model to generate the next to…

So instead of generating the next token from its own previous predictions (which is what it would do in real life), the code they used for the evaluation actually predicts from the ground truth?

Which would basically turn the model into a plainly normal LLM without any need for utilizing the brainwave inputs, right?

Re: BrainGPT turns thoughts into text

#144

Post by daniel_iversen »

mikpanko wrote: post #136

I did a PhD in brain-computer interfaces, including EEG and implanted electrodes. BCI research to a big extent focuses on helping paralyzed individuals regain communication. Unfortunately, EEG doesn’t provide sufficient signal-to-noise ratio to support good communication speeds outside of the lab with Faraday cages and days/weeks of de-noising including removing eye-movement artifacts in the recordings. This is a phy…

What’s your thoughts of Elon’s NeuraLink? Also, do you have an opinion on whether good AI algorithms (like in the article) can help filter out or parse a lot of the noise?

Re: BrainGPT turns thoughts into text

#145

Post by AndrewKemendo »

mikpanko wrote: post #136

I did a PhD in brain-computer interfaces, including EEG and implanted electrodes. BCI research to a big extent focuses on helping paralyzed individuals regain communication. Unfortunately, EEG doesn’t provide sufficient signal-to-noise ratio to support good communication speeds outside of the lab with Faraday cages and days/weeks of de-noising including removing eye-movement artifacts in the recordings. This is a phy…

I just did a two day ambulatory eeg and noted anytime I did anything that would be electrically noisy.

For example going through a metal detector or handling a phone.

Unsurprisingly one of their biggest sources of noise is handling a plugged in phone.

I think something like an EEG faraday beanie would actually work and adding accessory egocentric video would allow doctors to filter a lot of the noise out.

Re: BrainGPT turns thoughts into text

#146

Post by AndrewKemendo »

mike_hearn wrote: post #117
explaininjs wrote: post #108

Earlier quoted context omitted.

Interesting ploy. Present far-better-than-achieved results right on the front page with no text to explain their origin^, but make them poor enough quality to make it seem as if they might be real. ^ "Overall illustration of translate EEG waves into text through quantised encoding." doesn't count.

Urgh. And it gets worse from there. The bugs list on the repo has a closed and locked bug report from someone claiming that their code is using teacher forcing! https://github.com/duanyiqun/DeWave/issues/1 In a normal recurrent neural network, the model predicts token-at-a-time. It predicts a token, and that token is appended to the total prediction so far which is then fed back into the model to generate the next to…

This is a super important point and I think warrants a letter to the editor

Re: BrainGPT turns thoughts into text

#148

Post by demondemidi »

dexwiz wrote: post #53

Everyone is this thread immediately went to mind readers as interrogation. But what about introspection? Many forms of teaching and therapy exist because we are incapable of self analyzing in a completely objective way. Being able to analyze your thought patterns outside your own head could lead to all sorts of improvements. You could find which teaching techniques are actually the most effective. You could objective…

> Everyone is this thread immediately went to mind readers as interrogation.

Yes.

It's kind of hard to think about the upside of no longer having private thoughts.

I'm amazed you can go right to its benefits without realizing the universe-sized hole in the ethics of this.

But then again, that's techbro nature.

Re: BrainGPT turns thoughts into text

#150

Post by iamleppert »

mike_hearn wrote: post #117
explaininjs wrote: post #108

Earlier quoted context omitted.

Interesting ploy. Present far-better-than-achieved results right on the front page with no text to explain their origin^, but make them poor enough quality to make it seem as if they might be real. ^ "Overall illustration of translate EEG waves into text through quantised encoding." doesn't count.

Urgh. And it gets worse from there. The bugs list on the repo has a closed and locked bug report from someone claiming that their code is using teacher forcing! https://github.com/duanyiqun/DeWave/issues/1 In a normal recurrent neural network, the model predicts token-at-a-time. It predicts a token, and that token is appended to the total prediction so far which is then fed back into the model to generate the next to…

You’d be shocked how common this is in academia. Most of the time it goes undetected because the people writing the checks can’t be bothered to understand.
Post reply on HN