So an image, let’s suppose it was 100 pixels by 100 pixels image, that’s 10,000 pixels and each pixel is three channels RGB (red, green, blue in color), so that’s 30,000 numbers intensity in each channel in pixel that represents the image. imagine you wanted to detect birds in images. About 10 years later, Yesher Avenger took the same net and showed it actually worked for natural language, which was much bigger. It had embedding vectors that were only six components and a training set that was 112 cases, but it was a language model it was trying to predict the next turn in a string of symbols. And curiously, we did that by implementing a tiny language model. The special thing we did was used it to and showed it could develop good internal representations. "Many different groups discovered back propagation. This is an algorithm you developed with a couple of colleagues back in the 1980s.
So, I don’t really have any regrets over what I did." Until very recently, I thought this existential crisis was a long way off. It wasn’t really foreseeable - this stage of it wasn’t foreseeable. I think it was perfectly reasonable back in the '70s and '80s to do research on how to make artificial neural networks. I don’t think I made any had decisions in doing research.
In the end, I said maybe I had slight regrets, which got reported that I had regrets. And a couple things have led me to that conclusion and one of them is the performance of GPT-4."ĭo you have regrets that you were involved in making this? " tried very hard to get me to say I had regrets. They’re using back propagation and I think the brain’s probably not. "Over the last few months, I’ve changed my mind completely, and I think probably the computer models are working in a completely different way than the brain. The aim was to see if you could understand more about the brain by seeing what it takes to improve the computer models. I used to think that the computer models we were developing weren’t as good as the brain. "A second was, very recently, I’ve changed my mind a lot about the relationship between the brain and the kind of digital intelligence we’re developing.
0 kommentar(er)
