INVESTIGATION INTO EFFECTS OF DEVICE VARIATION ON PERFORMANCE OF OPTOELECTRONIC NEURAL NETWORKS

Free space optical links, using LEDs and photodiodes, have been studie d as a means of communication between neural layers in an analogue mul tilayered perceptron neural network architecture, trained using the ba ck-propagation learning algorithm. Simulation results on network learn ing and generalisation show that such networks are tolerant to as much as 75% variation in either the LED or photodiode responses.