Isabelle Guyon

Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos

2018 · arXiv (Cornell University)

Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analysis such as in health care applications. Despite their importance, it …

Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020

2021 · arXiv (Cornell University)

This paper presents the results and insights from the black-box optimization (BBO) challenge at NeurIPS 2020 which ran from July-October, 2020. The challenge emphasized the importance of evaluating derivative-free optimizers for tuning the hyperparameters of …

MetaREVEAL: RL-based Meta-learning from Learning Curves

2021 · INRIA a CCSD electronic archive server

International audience