Machine Learning for Analog Accelerators
A machine learning technique for evaluating materials used to make analog accelerators, whose lower power and faster speed can drive deep learning.
June 15, 2018
The Future of AI Needs Better Compute: Hardware Accelerators Based...
Analog memory for accurate, faster, lower power neural network training - a major step on the path to hardware accelerators for the next AI breakthroughs.
June 6, 2018
Expanding AI’s Field of Computer Vision at CVPR 2018
IBM Research AI will present multiple technical papers and host two workshops at CVPR 2018. Join us in Salt Lake City at booth #845.
June 4, 2018
Contrastive Explanations Help AI Explain Itself by Identifying What is...
An algorithm that can provide contrastive explanations for models such as deep neural networks to improve the explanations generated by AI technologies.
May 25, 2018
Pairing AI with Optical Scanning for Real-World Product Authentication
IBM Crypto Anchor Verifier couples innovations in AI and optical imaging for object authentication. Our first client GIA is using it to evaluate diamonds.
May 23, 2018
Machine Learning Can Treat Brain Disorders Where They Most Often...
A cloud-based automated machine learning approach to provide decision support for non-specialist physicians in treating brain disorders.
May 16, 2018
Talking to AI – Where natural language falls short
AI researchers are building the next generation of conversational AI interfaces by applying conversation science to user experience (UX) design.
May 7, 2018
Disentanglement of Latent Factors of Variation with Deep Learning
A principled approach for disentanglement of hidden factors from a large pool of unlabeled observations via unsupervised learning.
May 4, 2018
A CLEVER Way to Resist Adversarial Attack
New CLEVER scores can be used to compare the robustness of different neural networks against adversarial attack to help build more reliable AI systems.
May 2, 2018
Exploring Frontiers of AI at ICLR 2018
IBM Research shares recent discoveries in learning data representations for AI at the 6th International Conference on Learning Representations (ICLR 2018).
April 30, 2018
New Algorithm to Discover Eigenoptions in Reinforcement Learning
An algorithm that extends the use of eigenoptions to settings with stochastic transitions and raw sensory data, demonstrated using Atari games.
April 27, 2018