Intuition and Implementations for Gated Linear Networks

Intuition and Implementations for Gated Linear Networks(aiwabdn.github.io)

3 points by aiwabdn 5 years ago | 5 comments

aiwabdn 5 years ago |

This blog post details our interpretation of Gated Linear Networks, a new family of neural networks proposed by researchers at DeepMind. Implementations in JAX, NumPy, PyTorch and Tensorflow are here: https://github.com/aiwabdn/pygln

p1esk 5 years ago | |

What prevents you from scaling it up and achieving good results on Imagenet?

aiwabdn 5 years ago | | |

Main reason for now is that the cosine similarity used as context function is not suitable for natural images like those in Imagenet. We are experimenting some extensions based on convolutions for such use cases.