Bit is all we need: binary normalized neural networks (arxiv.org)

Screenshot of arxiv.org: Bit is all we need: binary normalized neural networks

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: Were RNNs all we needed?

Were RNNs all we needed?(arxiv.org)

466 points by beefman 2 years ago | 245 comments

arXiv paper proposing minimal LSTM and GRU variants without hidden-state gate dependencies that can be trained in parallel, rivaling recent sequence models.

rnn lstm gru transformers

Screenshot of arxiv.org: Neural Network Diffusion

Neural Network Diffusion (arxiv.org)

199 points by vagabund 2 years ago | 74 comments

Screenshot of arxiv.org: Transformers Are Bayesian Networks

Transformers Are Bayesian Networks (arxiv.org)

27 points by Anon84 7 months ago | 16 comments

Screenshot of arxiv.org: Transformers without normalization

Transformers without normalization (arxiv.org)

33 points by kaycebasques 1 year ago | 3 comments

Screenshot of arxiv.org: Kolmogorov Neural Networks can represent discontinuous functions

Kolmogorov Neural Networks can represent discontinuous functions (arxiv.org)

93 points by ubj 3 years ago | 27 comments

Screenshot of arxiv.org: Bayesian Flow Networks

Bayesian Flow Networks (arxiv.org)

106 points by albertzeyer 3 years ago | 18 comments

Looks similar

Were RNNs all we needed?(arxiv.org)

Neural Network Diffusion(arxiv.org)

Transformers Are Bayesian Networks(arxiv.org)

Transformers without normalization(arxiv.org)

Kolmogorov Neural Networks can represent discontinuous functions(arxiv.org)

Bayesian Flow Networks(arxiv.org)

Neural Network Diffusion (arxiv.org)

Transformers Are Bayesian Networks (arxiv.org)

Transformers without normalization (arxiv.org)

Kolmogorov Neural Networks can represent discontinuous functions (arxiv.org)

Bayesian Flow Networks (arxiv.org)