Abstract. This article underlines the learning and discrimination capabilities of a model of associative memory based on artificial networks of spiking neurons. Inspired from neuro...
We investigate when sparse coding of sensory inputs can improve performance in a classification task. For this purpose, we use a standard data set, the MNIST database of handwritte...
A conditioning graph is a form of recursive factorization which minimizes the memory requirements and simplifies the implementation of inference in Bayesian networks. The time com...
In this paper we present an automated method for classifying astronomical objects in multispectral wide-field images. The method is divided into three main tasks. The first one co...
Modern applications distributed across networks such as the Internet may need to evolve without compromising application availability. Object systems are well suited for runtime up...