COML Research team
Cognitive Machine Learning
- Leader : Emmanuel Dupoux
- Type : team
- Research center(s) : Paris
- Field : Perception, Cognition and Interaction
- Theme : Language, Speech and Audio
- Inria teams are typically groups of researchers working on the definition of a common project, and objectives, with the goal to arrive at the creation of a project-team. Such project-teams may include other partners (universities or research institutions)
The aim of the Cognitive Computing team is to reverse engineer human learning abilities, i.e., to construct effective and scalable algorithms which perform at least as well as humans, when provided with similar data, to study their mathematical and algorithmic properties and to test their empirical validity as models of humans by comparing their output with behavioral and neuroscientific data. The expected results are more adaptable and autonomous machine learning algorithm for complex tasks, and quantitative models of cognitive processes which can used to predict human developmental and processing data.
- Unsupervised language learning. Inspired by language learning ininfants, we develop unsupervised/weakly supervised learning algorithms which discover speech and language units from raw sensory data (speech and video of parent/infant interactions).
- Human/Machine Benchmarking. We construct cognitive tests designed to evaluate how an artificial system performs a complex function like language processing or reasoning and compare results with human performance on the same task and data.
International and industrial relations
The CoML team has working collaborations with the Cognitive Science Department at the Ecole Normale Supérieure, with MIT and CMU (USA), the RIKEN institute (Japan), MacQuarie University (Australia), the Brno institute of technology (Czeck Republic). It is involved in a data collection effort of infant data, the DARCLE community, involving laboratories in the USA, Canada and the Netherlands. We have collaborations with Facebook AI Research and Microsoft on unsupervised machine learning and human benchmarking and with IBM on speech technology applied to health care.