The testing and formal verification of black box software components is a challenging domain. The problem is even harder when specifications of these components are not available...
Indicators help actors to organise, orientate and navigate through complex environments by providing contextual information relevant for the performance of learning tasks. In this ...
To cope with large scale, agents are usually organized in a network such that an agent interacts only with its immediate neighbors in the network. Reinforcement learning technique...
— Optimal component analysis (OCA) uses a stochastic gradient optimization process to find optimal representations for general criteria and shows good performance in object reco...
Abstract— Designing effective behavioral controllers for mobile robots can be difficult and tedious; this process can be circumvented by using unsupervised learning techniques w...
The University of the Digital Society is based on interactions that facilitate learning in a new pragmatic context. Catalysts involved in the learning process replace the traditio...
The Support Vector Machine (SVM) is an acknowledged powerful tool for building classifiers, but it lacks flexibility, in the sense that the kernel is chosen prior to learning. Mul...
Marie Szafranski, Yves Grandvalet, Alain Rakotomam...