I used Keras implementation of the cosine restarts algorithm. I need to know the exact formula of the algorithm for my LaTeX manuscript. The documentation is here. The implementation differs (in terms of parameters) from the original paper they reference. I am not able to derive the formula from source code myself. Is someone able to help me with that? I tried feeding Chat-GPT with it but I can't verify the result.
Asked
Active
Viewed 5 times
