{"id":4,"date":"2011-12-08T11:55:34","date_gmt":"2011-12-08T11:55:34","guid":{"rendered":"http:\/\/project.inria.fr\/template1\/?page_id=4"},"modified":"2023-07-10T16:32:09","modified_gmt":"2023-07-10T14:32:09","slug":"home","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/hyaiai\/","title":{"rendered":"Home"},"content":{"rendered":"

HyAIAI is an Inria Project Lab<\/a> about the design of novel, interpretable approaches for Artificial Intelligence. It lasted between Oct. 2019 and June 2023.<\/p>\n

Summary:<\/strong> Recent progress in Machine Learning (ML) and especially Deep Learning has made ML pervasive in a wide rang\"\"<\/a>e of applications. However, current approaches rely on complex numerical models: their decisions, as accurate as they may be, cannot be easily explained to the layman that may depend on these decisions (ex: get a loan or not). In the HyAIAI IPL, we tackle the problem of making \u201cInterpretable ML\u201d by studying and designing hybrid approaches that combine state-of-the-art numeric models with explainable symbolic models. More precisely, our goal is to be able to integrate high-level (domain) constraints in ML models, to give model designers information on ill-performing parts of the model, and to give the layman\/practitioner understandable explanations on the results of the ML model.<\/p>\n

Inria teams involved:<\/strong><\/p>\n