YUN, Junwoo

Hi @awni , rebased and make cos loss to remain on this pr. Also commented on #324 based on my implementation. Thanks :)

> @Jyun1998 are you still planning to follow up on this? https://github.com/keras-team/keras/blob/v2.14.0/keras/losses.py#L1162-L1236 Hi awni, according to common tensorflow and pytorch implementaiton, the functions are composed of doing l2 norm to...

> @Jyun1998 got it. We should keep it simple until we see that we need more features. Could you follow the [PyTorch cosine similarity](https://pytorch.org/docs/stable/generated/torch.nn.functional.cosine_similarity.html) loss? I think that one covers...

> > Even though there's also margin for pytorch F.cosine_similarity > > I don't see the margin in the docs? Is it in the source code? > > https://pytorch.org/docs/stable/generated/torch.nn.CosineEmbeddingLoss.html#torch.nn.CosineEmbeddingLoss

> Also could you rebase and resolve conflicts? Am I correct that losses test codes are gone? --- nvm found new losses test file

> Also could you rebase and resolve conflicts? Could you check? Thanks :)

Hi @angeloskath, thanks for the re-reviewing the issues and happy new year. I agree with you on the point that your SinusoidalPositionalEncoding is for encoding positions. However, my implementation is...