HyAIAI is an Inria Project Lab about the design of novel, interpretable approaches for Artificial Intelligence. It lasted between Oct. 2019 and June 2023.
Summary: Recent progress in Machine Learning (ML) and especially Deep Learning has made ML pervasive in a wide rang
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 “Interpretable ML” 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.
Inria teams involved:
- Lacodam (coordination)
- Magnet
- Multispeech
- Orpailleur
- Scool (formerly SequeL)
- TAU
More information about the project here.
Contact : hyaiai @ inria dot fr
