Negative log likelihood

What is it?

Advantage Actor Critic (A2C) implementation

Internet is full of very good resources to learn about reinforcement learning…

GLU: Gated Linear Unit implementation

From paper to code

How to add uncertainty to your neural network

Recently in my job I have been told to add uncertainty to our models, to find a…

Advantage Actor Critic continuous case implementation

Simple PPO implementation

Back with another simple implementation for reinforcement learning. I’m far from being an expert, but I hope you…

Everything you wish to know about BatchNorm

What is BatchNorm?

How to speed up pandas groupby

As you can see from the notebook by using “df.values” and building the groups our self is 3–4 times faster.

Ghost BatchNorm explained

From paper to code

The reparameterization trick with code example

First time I hear about this (well, actually first time it was readen…) I…