Goal: To develop a new learning paradigm for Artificial Intelligence (AI) that learns like humans in an adaptive, robust, and continuous fashion.
Summary: The new learning paradigm will be based on a new principle of machine learning, which we call the Bayes-Duality principle and will develop during this project. Conceptually, the new principle hinges on the fundamental idea that an AI should be capable of efficiently preserving and acquiring the relevant past knowledge, for a quick adaptation in the future. We will apply the principle to representation of the past knowledge, faithful transfer to new situations, and collection of new knowledge whenev
Funding and Duration: Funding of ≅ 2.76 Million USD approved is granted through the JST-CREST and French ANR 's Japan-French joint research calls . The Japan side is awarded JPY 249,300,000 (≅ USD 2.23 million), and is led by Mohammad Emtiyaz Khan as the research director, and Kenichi Bannai and Rio Yokota as the two Co-PIs. The France side is awarded EUR 464,000 (USD 530,000) and is led by Julyan Arbel . The project will run for a total of 5½yrs, starting from Oct. 1, 2021 to March 31, 2026. Follow @BayesD
Emtiyaz Khan's Homepage
Duality Principles for Modern ML
Siddharth Swaroop
Thomas Möllenhoff | About
Dharmesh Tailor
Thomas Möllenhoff | About
Peter Nickl