Approximate Probabilistic Neural Networks with Gated Threshold Logic

Abstract

This paper proposes a novel architecture for approximate probabilistic neural networks (PNNs) based on gated threshold logic (GTL). The proposed approach achieves competitive classification accuracy with reduced computational complexity compared to conventional PNNs. Experimental results on standard benchmarks demonstrate the effectiveness of the method in terms of speed and accuracy, suggesting its suitability for near-sensor edge processing and low-power applications.