Scaling laws for transfer learning. Transfer learning is when you take a neural network, usually one someone else has already built and that works for whatever they built it for, and train it on your own data. "Scaling laws", on the other hand, is when increasing the size of one thing increases something else by some exponential value, although the exponent can be a fraction. https://arxiv.org/abs/2102.01293
Server run by the main developers of the project It is not focused on any particular niche interest - everyone is welcome as long as you follow our code of conduct!