Research

Intel AI Research is pushing the limits of artificial intelligence and computing at every level, from atomic physics to data-center orchestration. We make big bets and take a systems view of AI: our research spans foundational work in machine learning algorithms and computer architecture to applied research in computer vision, autonomous driving, and distributed learning systems.

Recent Publications

On Training Flexible Robots using Deep Reinforcement Learning

Zach Dwiel, Madhavun Candadai, Mariano Phielipp
View Publication

Goal-conditioned Imitation Learning

Yiming Ding, Carlos Florensa, Mariano Phielipp, Pieter Abbeel
#Reinforcement Learning (RL)
View Publication

Channel Attention Networks

##CVPR2019
View Publication

Using A Priori Knowledge to Improve Scene Understanding

##CVPR2019
View Publication

Softmax* Optimizations for Intel® Xeon® Processor-based Platforms

#re:MARS
View Publication

Hierarchical Policy Learning Is Sensitive To Goal Space Design

##ICLR2019
View Publication

RL Coach

Reinforcement Learning Coach is an an open source research framework for training and evaluating reinforcement learning (RL) agents that uses the processing power of multi-core CPUs to enable efficient training of RL agents.

Overview • GithubDocumentation

Distiller

Network compression can reduce the memory footprint of a neural network, increase its inference speed and save energy. Distiller provides a PyTorch environment for prototyping and analyzing compression algorithms, such as sparsity-inducing methods and low-precision arithmetic.

OverviewGithubDocumentation

NLP Architect

Natural Language Processing (NLP) Architect is an open-source Python library for exploring the state-of-the-art deep learning topologies and techniques for natural language processing and natural language understanding. It is intended to be a platform for future research and collaboration.

OverviewGithubDocumentation

CARLA

CARLA is an open-source simulator for autonomous driving research that supports development, training, and validation of autonomous urban driving systems.

Overview • GithubDocumentation

Loihi

Loihi is a self-learning neuromorphic test chip developed by Intel Labs that combines training and deployment in one package and was designed for use in research applications.

Overview

Research Programs

Intel AI Research is inviting a select group of applicants to join its research labs in California for a one year residency to push the boundaries of artificial intelligence.

Learn More