How many deep learning neural networks can you effectively run on a single GPU? First of all, there is no simple answer to this question. Some big models may not run on an average GPU with 11–12GB of RAM even separately. However, suppose your model is relatively small, e.g. it is a classifier with the following number of variables: 1e5–1e6. …

PART 004: One line game changer — MP decorator — Every now and then I manage to write a piece of code that really makes me smile for a long time. It happens about twice a year, sometimes more often. The shorter and more useful the code is, the better. …

PART 003: Tried to keep it simple. Failure and success. — When I start to solve a new machine learning task with Python and TensorFlow, at the beginning I try to keep things simple. I focus on the core of the problem and try to isolate it. Usually it is very good to start with the minimum amount of the data…

Part 002: Building the Cards Neural Network — Let’s build a neural network (NN) for the task introduced in my previous post. I expect the network to learn an algorithm of a poker hand ranking from the given examples. …

Part 001: Why to put the Neural Nets on Poker? — Implementing reinforcement learning in such complex environment is not straightforward, but I can split the problem into smaller factors. For sure, it will take time. In the meantime, I will report the progress of the project and my observations here in the subsequent posts. In general, I’ll have to think…

It is the right time to give the pypoks project a new “medium”. In the following posts, you will find some info, concepts & updates about the project. pypoks is an attempt to implement reinforcement learning into deep neural networks for poker game environment. I will use Python with Tensorflow mainly. You may have a look at the code here.