For deep learning training, a decentralized approach can boost performance 10x performance over a centralized approach without additional complexity, finds new study.
IBM scientists and academic collaborators recently developed an AI-based algorithm able to provide more accurate, timely product recommendations.
A new supervised learning algorithm developed to solve a well-known problem in AI called textual grounding will help AI interact more naturally.
To make programming TJBot easier and more accessible, we developed the TJBot Swift Playground.
A new methodology from IBM Research AI reduces the discrimination present in datasets used to train AI algorithms so they perpetuate as little inequity as possible.
IBM researchers conducted experiments to prove how dictionaries can be used to teach AI systems faster and more efficiently than previously possible.
The Lancet’s EBioMedicine journal published a study led by scientists from IBM Research-Australia and the University of Melbourne marking important progress in personalized seizure forecasting with AI.
IBM and EPFL scientists have just published a scheme that learned how to distinguish the difference between cats and dogs using a 30 Gigabyte training dataset in less than a...
At the NIPS 2017 Conference, IBM researchers present a web-based app which takes the idea of relating organic chemistry to a language and applies state-of-the-art neural machine translation methods to...