Grzego

handwriting-generation

Implementation of handwriting generation with use of recurrent neural networks in tensorflow. Based on Alex Graves paper (https://arxiv.org/abs/1308.0850).

async-rl

Variation of "Asynchronous Methods for Deep Reinforcement Learning" with multiple processes generating experience for agent (Keras + Theano + OpenAI Gym)[1-step Q-learning, n-step Q-learning, A3C]

mnist-handwriting-dataset

Handwritten version of MNIST dataset. Generated using LSTM neural network.

agh-max-clique-genetic

Genetic algorithm for finding maximum clique in graph.

agh-miss-project

Multiagent simulation project for academic purposes.

game-level-gan

Generating balanced multiplayer game levels with GANs and RL.

agh-trip-planner

Web application for planning a trip.

erlang-ann

Simple artificial neural network written in erlang.

grzego.github.io

nn-workshop

Warsztaty z sieci neuronowych