News for hackers. Stuff that matters.
Re:Decomposing Language Models into Understandable Components by Animats on Sunday October 08, 2023 @03:36AM (#37808583)
> We find that the features that are learned are largely universal between different models, so the lessons learned by studying the features in one model may generalize to others.

Hm. I wish they'd said more about that. Does that mean they found the same feature recognizers when training with the same training set? Or what? This tells us something, but what does it tell us?

Re:Decomposing Language Models into Understandable Components by karxxm on Sunday October 08, 2023 @06:53AM (#37809427)
Some architectures are relatively well understood. Eg in CNNs, the first layers detect low level features like edges, gradients, etc. The next layer then combines these features to more complex structures like corners or circles. Next layer will combine these features to even higher level features and so on. [1]

Typically, you can take a pre-trained model and retrain it on your new dataset by only changing the weights of the last layer(s).

Some loss functions even measures the difference between the high-level features of two images, typically extracted from a pre-trained CNN (Perceptual Loss).

[1]Matt Zeiler did an amazing work on these findings 10 years ago (https://arxiv.org/abs/1311.2901).