In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
The solving of least square systems is a useful operation in neurocomputational modeling of learning, pattern matching, and pattern recognition. In these last two cases, the soluti...
Successful image reconstruction requires the recognition of a scene and the generation of a clean image of that scene. We propose to use recurrent neural networks for both analysi...
We have proposed that the basal ganglia act as the central switching mechanism for the action selection system of the vertebrate brain. Simulation of our functional model of basal ...
Mark D. Humphries, Tony J. Prescott, Kevin N. Gurn...
Most of source separation methods focus on stationary sources, so higher-order statistics is necessary for successful separation, unless sources are temporally correlated. For non...