In Pavlovian and instrumental conditioning, rewards typically come seconds after reward-
triggering actions, creating an explanatory conundrum known as the distal reward problem …

A novel method is presented to allow a machine controller to evolve while the machine is
acting in its environment. The method uses a single spiking neural network with a minimum …

Contemporary image recognition schemes either rely on single-feature recognition or focus
on solving multi-feature recognition using complex computational approaches. Furthermore …

A novel method for the creation of machine controllers autonomously is presented. The
method is based on reward values which can represent the internal state of the machine or …

Understanding how sequences are learned and encoded is a key component to
understanding cognition. We present a recruitment model in which sequences are learned …

A novel methodology to create a powerful controller for robots that minimises the design
effort is presented. We show that using the feedback from the robot itself, the system can …

Au delà de ses fonctions primaires régulatrices et sensori-motrices, le cerveau est un
formidable système adaptatif capable de développer des réponses nouvelles dans des …

Since machine learning has become a tool to make more efficient design of sophisticated
systems, we present in this paper a novel methodology to create powerful neural network …

Manually programming machines that are required to solve complex problems is
timeconsuming. Designing machine controllers may also demand skills that are not …