Learning of local predictable representations in partially learnable environments

Mathieu Lefort (1, 2) , Alexander Gepperth (1, 2)

1 RV - Robotique et Vision
2 Flowers - Flowing Epigenetic Robots and Systems

PROPRE is a generic and cortically inspired framework that provides online input/output relationship learning. The input data flow is projected on a self-organizing map that provides an internal representation of the current stimulus. From this representation, the system predicts the value of the output target. A predictability measure, based on the monitoring of the prediction quality, modulates the projection learning so that to favor learning of representations that are helpful to predict the output. In this article, we study PROPRE when the input/output relationship is only defined in a small subspace of the input space, that we define as a partially learnable environment. This problem, which is not typical of the machine learning field, is however crucial for the robotic developmental field. Indeed, robots face high dimensional sensory-motor environments where large areas of these sensory-motor spaces are not learnable since a motor action cannot have a consequence on every perception each time. We show that the use of the predictability measure in PROPRE leads to an autonomous gathering of local representations where the input data are related to the output value, thus providing good classification performance as the system will learn the input/output function only where it is defined.

Mots clés: Self Organizing Maps; Prediction Neural Networks; Supervised learning algorithm

Domaines: Réseau de neurones [cs.NE]; Apprentissage [cs.LG]

Mathieu Lefort, Alexander Gepperth. Learning of local predictable representations in partially learnable environments. The International Joint Conference on Neural Networks (IJCNN), Jul 2015, Killarney, Ireland. ⟨hal-01205611⟩