Combine deep neural nets with a probabilistic model. Construct a Variational Autoencoder (VAE) using TFP Layers and Keras.
Here’s how ↓ https://t.co/dSvw9DoYBx
@seanjtaylor Tensorflow Probability offers a second-order solver for L2 regularized GLMs. In O(days) we'll release a proximal newton type method for L1 regularized GLMs (ie, similar to GLMNet).
https://t.co/oNOYlLVXVu