Dual nature hidden layers neural networks "a novel paradigm of neural network architecture"

We present here a new scheme to construct a neural network architecture based on the physiological properties of a biological neuron for enhancing its performance. The new scheme divides every hidden layer into two-parts to facilitate the processing of 0 and 1 separately and reduces the total number of interconnections considerably. The first part consists of units that receive signals only from ´1 state´ units of the immediately lower layer and are responsible for producing excitation units in the output layer i.e. the ´1 state´ and the second part consists of units that also receive signals only from ´1 state´ units from the immediately lower layers that are responsible for producing inhibition of the units in the output layer i.e. the ´0 states´. The resulting architecture converges fast, produces more reliable results and reduces the computational burden considerably when compared to fully connected neural networks