In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Abstract. Recent experimental observations of spiketiming-dependent synaptic plasticity (STDP) have revitalized the study of synaptic learning rules. The most surprising aspect of ...
Inthis article westudy the fundamental category (Goubault and Raussen, 2002 Goubault, 2002) of a partially ordered topological space (Nachbin, 1965 Johnstone, 1982), as arising in ...
Surrogate maximization (or minimization) (SM) algorithms are a family of algorithms that can be regarded as a generalization of expectation-maximization (EM) algorithms. There are...
We address the problem of learning distance metrics using side-information in the form of groups of "similar" points. We propose to use the RCA algorithm, which is a sim...