ADCG: Solver for sparse inverse problems in computational imaging

Apache Spark: GraphX: A framework for graph large-scale distribured graph structured computation

Berkeley NLP tools: High-performing systems for a number of NLP tasks, including syntactic parsing, entity analysis, structured prediction, OCR, language modeling, and word alignment.

BLOG probabilistic programming language (PPL): A general purpose probabilistic programming language designed for representing relations and uncertainties among real world objects.

Boda: A framework for productively and portably producing high-efficient implementations of DNN/CNN

CAFFE: Open source deep learning

CoCoA: A Framework for Communication-Efficient Distributed Optimization

Computation Graph Toolkit (CGT): Computation Graph Toolkit (CGT) is a library for evaluation and differentiation of functions of multidimensional arrays. Source code is available on GitHub.

CycleGAN: Torch implementation for learning an image-to-image translation without input-output pairs

DeepBox: DeepBox object proposals (ICCV 15')

Guided Policy Search (GPS): This code-base implements the guided policy search algorithm and LQG-based trajectory optimization. It includes a complete robot controller and sensor interface for the PR2 robot via ROS, and an interface for simulated agents in Box2D and Mujoco.

iGAN: Interactive Image Generation via Generative Adversarial Networks

Iterative Error Feedback (IEF): Human Pose Estimation With Iterative Error Feedback

Keystone ML: Framework for construction of large scale, end-to-end, machine learning pipelines with Apache Spark.

LRCN: Deep video / vision sequene learning

LSDA: Large-scale deep visual detection

NEXT: Simplifies the deployment and evaluation of active learning algorithms that use human feedback (in collaboration with University of Wisconsin)

pix2pix: Torch implementation for learning a mapping from input images to output images

pytorch-CycleGAN-and-pix2pix: PyTorch implementation for both unpaired and paired image-to-image translation.

RAPTOR: Adaptive robotic detector learning

Ray: A distributed system unifying the machine learning ecosystem. Ray includes libraries for hyperparameter search, reinforcement learning, and model training.

rllab: rllab is a framework for developing and evaluating reinforcement learning algorithms.

SparkNet: Distributed Neural Networks for Spark

Splash: Splash: User-friendly Programming Interface for Parallelizing Stochastic Algorithms

trajopt: Trajectory Optimization for Motion Planning: trajopt is a software framework for generating robot trajectories by local optimization.

Zumy Robot: Open source hardware and software for small tracked mobile robot using ROS