For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.

Microsoft Program Synthesis using Examples SDK is a framework of technologies for the automatic generation of programs from input-output examples. This repo includes samples and sample data for the…

Protocol Buffers - Google's data interchange format

A tiny, educational library for secure multi-party computation (in pure Python).

Statsmodels: statistical modeling and econometrics in Python

A simple package to do symbolic math (focus on code gen and DSLs)

A SMPC companion library for Syft

Perform data science on data that remains in someone else's server

A curated list of practical financial machine learning tools and applications.

Large-scale, multi-GPU capable, kernel solver

Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Implementations of selected inverse reinforcement learning algorithms.

Minimal and Clean Reinforcement Learning Examples

Deep Learning and Reinforcement Learning Library for Scientists and Engineers

Library for training machine learning models with privacy for training data

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

An adversarial example library for constructing attacks, building defenses, and benchmarking both

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

An optimizer that trains as fast as Adam and as good as SGD.

Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning / ICLR 2020

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Code for the paper "Quantifying Transfer in Reinforcement Learning"

A list of recent papers regarding deep reinforcement learning

Reinforcement learning resources curated

autodp: A flexible and easy-to-use package for differential privacy

Archive of my notes taken at lectures in IIITH

Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

machine learning for artists

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …