Error minimization in Phase-Based Neurons
Ionel-Bujorel Păvăloiu, Paul Dan Cristea · 2012
Complex-Valued Neural Networks are extensions of the classical Neural Networks. They have complex-valued weights, accept complex inputs and have more computational power than the classical ones. We discuss in this paper the training for Phase-Based Neurons, neural processing elements similar to Universal Binary Neurons, that uses as weights and bias complex numbers with unit magnitude, the phase being the only tunable parameter.