Machine learning for sequential interactive models
Résumé rédigé par
Directeur de thèse:
Unité de recherche UMR 7606 Laboratoire d'informatique de Paris 6
Recently, a new family of algorithms called “sequential prediction models” has emerged in machine learning. The motivation behind their development is that, while there is a plethora of standard algorithmic solutions for supervised and unsupervised training, most of the methods learn a monolithic predictor function, that is each test instance is processed in a single-step, atomic process. Some recent studies have proposed a different paradigm in which prediction is reformulated as a sequential decision process, and for which learning the predictor function corresponds to solving a dynamic control problem. A very interesting point is that sequential learning models can naturally take into account an explicit interaction with an expert, at two different levels :
- while sequential models behave "like experts", humans can be use to guide the learning process, and - sequential models can naturally interact with humans by asking questions
The Thesis will be organized on two axis : attention and transformation (learning a unique model able to learn where to get relevant information but also how to transform collected information), and interaction with users.