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.