We show that an ongoing locomotor pattern can that the physiology of the lamprey's spinal system generalizes to be modulated by application of discrete electrical stimuli to l...
R. Jacob Vogelstein, Ralph Etienne-Cummings, Nitis...
A direct adaptive neural network control system with and without integral action term is designed for the general class of continuous biological fermentation processes. The control...
Ieroham S. Baruch, Petia Georgieva, Josefina Barre...
Abstract—Traditionally, random access protocols have been designed and studied by assuming simple models for the physical layer. We introduce a reception model that incorporates ...
Recent studies show that state-space dynamics of randomly initialized recurrent neural network (RNN) has interesting and potentially useful properties even without training. More p...
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...