PROJECT TITLE :

VLSI Implementation of a Bio-Inspired Olfactory Spiking Neural Network

ABSTRACT:

This paper presents a coffee-power, neuromorphic spiking neural network (SNN) chip that can be integrated in an electronic nose system to classify odor. The proposed SNN takes advantage of sub-threshold oscillation and onset-latency illustration to cut back power consumption and chip area, providing a additional distinct output for every odor input. The synaptic weights between the mitral and cortical cells are modified in step with an spike-timing-dependent plasticity learning rule. During the experiment, the odor knowledge are sampled by a business electronic nose (Cyranose 320) and are normalized before coaching and testing to confirm that the classification result's only caused by learning. Measurement results show that the circuit solely consumed a median power of roughly three.vi $murm W$ with a one-V power provide to discriminate odor information. The SNN has either a high or low output response for a given input odor, creating it easy to work out whether or not the circuit has made the correct decision. The measurement results of the SNN chip and some well-known algorithms (support vector machine and also the K-nearest neighbor program) is compared to demonstrate the classification performance of the proposed SNN chip.The mean testing accuracy is eighty seven.fifty nine% for the data employed in this paper.