Approximate Probabilistic Neural Networks with Gated Threshold Logic

TL;DR

This paper introduces an approximate probabilistic neural network that uses gated threshold logic and memristive crossbar architecture to simplify hardware implementation for classification tasks.

Contribution

It presents a novel hardware-efficient approximation of PNN by replacing exponential functions with gated threshold logic and employing weight normalization and quantization.

Findings

Reduces circuit complexity significantly

Achieves efficient weight normalization and quantization

Enables hardware implementation of PNNs

Abstract

Probabilistic Neural Network (PNN) is a feed-forward artificial neural network developed for solving classification problems. This paper proposes a hardware implementation of an approximated PNN (APNN) algorithm in which the conventional exponential function of the PNN is replaced with gated threshold logic. The weights of the PNN are approximated using a memristive crossbar architecture. In particular, the proposed algorithm performs normalization of the training weights, and quantization into 16 levels which significantly reduces the complexity of the circuit.