Biocultural learning – beyond ecological knowledge transfer

Hierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents

This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...

Knowledge Transfer in Reinforcement Learning

Knowledge Transfer in Artificial Learning

This document presents the main research problems addressed during my PhD studies. All these researches are led inside the two teams DBWeb in Télécom ParisTech and LInK (Learning and Integration of Knowledge) in AgroParisTech, both located in Paris, and supervised by Pr. Jean-Louis Dessalles and Pr. Antoine Cornuéjols. My researches focus on learning theory both in the perspective of symbolic m...

Beyond Knowledge Management: Introducing Learning Management Systems

EXECUTIVE SUMMARY In the knowledge economy, a firm’s intellectual capital represents the only sustainable source of competitive advantage; accordingly, the ability to learn, and to manage the learning process are key success factors for firms. The knowledge management approach to learning in organizations has achieved limited success, primarily because it has focused on knowledge as a resource ...

Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer

Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new multiclass problem. Our main idea is to identif...