Despite all the progress in neural networks the technology is still brittle and sometimes difficult to apply. Automatic construction of networks and proper initialization of their...
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generati...
Abstract The Little-Hopfield neural network programmed with Horn clauses is studied. We argue that the energy landscape of the system, corresponding to the inconsistency function f...
Saratha Sathasivam, Wan Ahmad Tajuddin Wan Abdulla...
Evolving recurrent neural networks for behavior control of robots equipped with larger sets of sensors and actuators is difficult due to the large search spaces that come with the ...
Abstract. In this paper, neural networks trained with the back-propagation algorithm are applied to predict the future values of time series that consist of the weekly demand on it...