We describe the results of a research on the effect of weight-decay (WD) in input selection methods based on the analysis of a trained multilayer feedforward network. It was propos...
In this work new Decision-Feedback (DF) Neural Equalizers (DFNE) are introduced and compared with classical DF equalizers and Viterbi demodulators. It is shown that the choice of ...
Elio D. Di Claudio, Raffaele Parisi, Gianni Orland...
In modelling the development of the oculomotor control system using neural networks, it is important to determine the appropriate cost function on which to train the models. Whilst...
In this paper we investigate the performance of a Computer Aided Diagnosis (CAD) system for the detection of clustered microcalcifications in mammograms. Our detection algorithm co...
It has been shown that self-organized maps, when adequately trained with the set of integers 1 to 32, lay out real numbers in a 2D map in an ordering that is superior to any of the...
: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
Abstract. For a network of spiking neurons with reasonable postsynaptic potentials, we derive a supervised learning rule akin to traditional error-back-propagation, SpikeProp and s...
Sander M. Bohte, Joost N. Kok, Johannes A. La Pout...
One of the attractive feature of Self-Organizing Maps (SOM) is the so-called "topological preservation property": observations that are close to each other in the input s...
This paper describes a novel image registration method for movementcorrection of fMR time-series. It is important to align the fMR images in the time-series before time-dependent a...