Beckschen

imgaug

Image augmentation for machine learning experiments.

reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.

chess-alpha-zero

Chess reinforcement learning by AlphaGo Zero methods.

emotion-recognition-neural-networks

Emotion recognition using DNN with tensorflow

Paper_Notes

This will contain my notes for research papers that I read.

topicsne

t-SNE experiments in pytorch

pseudo-3d-pytorch

pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported

pseudo-3d-residual-networks

Pseudo-3D Convolutional Residual Networks for Video Representation Learning

CS231n

my assignment solutions for CS231n Convolutional Neural Networks for Visual Recognition

jaer

Java tools for Address-Event Representation (AER) neuromorphic vision and audio sensor processing

ImageAugmentation

Image augmentation for randomly rotating, shearing, translating and changing lighting conditions.

DeepReinforcementLearningThatMatters

Accompanying code for "Deep Reinforcement Learning that Matters"

Training-Neural-Networks-for-Event-Based-End-to-End-Robot-Control

TUM Master’s thesis: Steering a robot with an event-based vision sensor in a lane-keeping task using methods such as Deep Reinforcement Learning or Spiking Neural Networks.

Behavior-Cloning

end to end learning for self-driving

ReproducibilityInContinuousPolicyGradientMethods

These are experiments for examining reproducibility in Policy Gradient RL algorithms in Continuous domains. Mainly using the Rllab implementation.

MIPS-in-Verilog

An implementation of MIPS single cycle datapath in Verilog.

Single-Cycle-MIPS

Single Cycle MIPS Implementation in Verilog

LSTM-acc-predict