This paper addresses the following question: ``What neural circuits can emulate the monosynaptic correlogram generated by a direct connection between two neurons?'' The ...
Francisco J. Veredas, Francisco J. Vico, Jos&eacut...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
—Since machine learning has become a tool to make more efficient design of sophisticated systems, we present in this paper a novel methodology to create powerful neural network ...
We studied the dynamics of a neural network which have both of recurrent excitatory and random inhibitory connections. Neurons started to become active when a relatively weak trans...
This paper is focused on determining the parameters of radial basis function neural networks (number of neurons, and their respective centers and radii) automatically. While this ...