Sparse Matrix Multiplication in JAX

In this post I’ll share my sparse matrix multiplication implementation in JAX, which could be useful for other problems besides implementing graph neural networks.

Implementing Graph Neural Networks with JAX

In this post I explain how to implement two different Graph Neural Networks using JAX. I start with an introduction to JAX and move to the implemententations of Graph Convolutional Neural Networks and Graph Attention Networks.

Neural art style transfer in Tensorflow

In order to practise a little bit with Tensorflow I have implemented the paper A Neural Algorithm of Artistic Style. I think it is an easy algorithm to code, and I encourage all the people who want to learn about Deep Learning or the ones who are trying to learn how to use a new framework to implement it themselves.

Reverse a Torch Tensor

Reversing a Tensor in Torch is not as easy as it is with Numpy, this is my one line code to reverse a Tensor in one dimension.