BoltzmannBrain

self-driving

Machine learning models for self-driving cars

design-patterns-for-humans

Design Patterns for Humans™ - An ultra-simplified explanation

nupic.research

Experimental algorithms. Unsupported.

abs_fetcher

Fetching paper abstracts for downstream NLP

blackdrops

Code for the Black-DROPS algorithm: "Black-Box Data-efficient Policy Search for Robotics", IROS 2017/ICRA 2018

boltzmannbrain.github.io

lavin.io

boltzmannbrain.github.ioOLD

{ Personal } website.

edward

A library for probabilistic modeling, inference, and criticism. Deep generative models, variational inference. Runs on TensorFlow.

Gen

github-issue-templates

:symbols: A collection of GitHub issue and pull request templates

GPflow

Gaussian processes in TensorFlow

gpmp2

Gaussian Process Motion Planner 2

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-http-api

API to access OpenAI Gym from other languages via HTTP

hack

⛷ Dead simple CSS framework.

hacker-laws

💻📖 Laws, Theories, Principles and Patterns that developers will find useful. #hackerlaws

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.

mltrl

Repository for the ML Technology Readiness Levels framework

models

Models built with TensorFlow

moveit

The MoveIt! motion planning framework

NAB

The Numenta Anomaly Benchmark

nn-visualizer

nupic

Numenta Platform for Intelligent Computing: a brain-inspired machine intelligence platform, and biologically accurate neural network based on cortical learning algorithms.

prednet

Code and models accompanying "Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning"

pyro

Deep universal probabilistic programming with Python and PyTorch

segmentation_models.pytorch

Segmentation models with pretrained backbones. PyTorch.

tensorflow

Computation using data flow graphs for scalable machine learning

thank-you-github

An open letter of gratitude to GitHub

TikZ

Turing.jl

Bayesian inference with probabilistic programming