DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.

A snake game trained using simple deep learning implemented in client side javascript.

Swift port of ConvnetJS. [Work in progress]

🤖CNN卷积神经网络 实现汽车🚘logo图像识别

ConvNetJS neural networks translated to U++ framework.

使用CIFAR-10数据集✈️🚗🐦🐈🦌🐶🐸🐎🚢🚛在浏览器训卷积神经网络

A machine-learning experiment using ConvNetJS.

use ConvNetJS on MNIST digits

A repository containing solutions to the challenges presented in the course MIT 6.S094: Deep Learning for Self-Driving Cars

AI for create paintings from images.

Exploring social behavior with qLearning agents

Neural network to facial expression recognition

DeepTraffic is a gamified simulation of typical highway traffic. The task is to build a neural agent – more specifically design and train a neural network that performs well on high traffic roads. The neural network controls one of the cars and learns how to navigate efficiently to go as fast as possible.