Matrix factorization into the product of lowrank matrices induces non-identifiability, i.e., the mapping between the target matrix and factorized matrices is not one-to-one. In th...
POMDPs are the models of choice for reinforcement learning (RL) tasks where the environment cannot be observed directly. In many applications we need to learn the POMDP structure ...
We introduce into the classical Perceptron algorithm with margin a mechanism of unlearning which in the course of the regular update allows for a reduction of possible contributio...
Temporal difference (TD) algorithms are attractive for reinforcement learning due to their ease-of-implementation and use of "bootstrapped" return estimates to make effi...
Online learning algorithms have recently risen to prominence due to their strong theoretical guarantees and an increasing number of practical applications for large-scale data ana...
We provide a novel view of learning an approximate model of a partially observable environment from data and present a simple implemenf the idea. The learned model abstracts away ...
We propose in this paper a new method to compute indicators based on models transformations. We use the concept of modeled trace and trace-based system to design an indicator. We u...
Emotions have a functional relevance to learning and achievement. Not surprisingly then, affective diagnoses are an important aspect of expert human mentoring. Computerbased learni...
ARIADNE is a European foundation that aims to foster "Share and Reuse" of learning resources. To support this goal, ARIADNE has created an infrastructure for managing lea...