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...
This research introduces a general class of functions serving as generalized neuron models to be used in artiļ¬cial neural networks. They are cast in the common framework of comp...
Sorting of the extracellularly recorded spikes is a basic prerequisite for analysis of the cooperative neural behavior and neural code. Fundamentally the sorting performance is deļ...
Alexey N. Pavlov, Valeri A. Makarov, Ioulia Makaro...
Abstract. A convolutional network architecture termed sparse convolutional neural network (SCNN) is proposed and tested on a real-world classification task (car classification). In...
This paper presents our approach to the rule extraction problem from trained neural network. A method called REX is briefly described. REX acquires a set of fuzzy rules using an ev...