We derive an optimal learning rule in the sense of mutual information maximization for a spiking neuron model. Under the assumption of small fluctuations of the input, we find a s...
We introduce the mixture of Gaussian processes (MGP) model which is useful for applications in which the optimal bandwidth of a map is input dependent. The MGP is derived from the...
Abstract. An architecture for achieving word recognition and incremental learning of new words in a language processing system is presented. The architecture is based on neural ass...
An audio fingerprint is a compact representation of the perceptually relevant parts of audio content. A suitable audio fingerprint can be used to identify audio files, even if ...
The dater equalities constitute a well-known tool which allows the description of Timed Event Graphs in the field of (max, +) algebra. This paper gives an equivalent model in the...
Abdelhak Guezzi, Philippe Declerck, Jean-Louis Boi...