# Binarized neural network of diode array with high concordance to vector–matrix multiplication

## TL;DR

This paper introduces a binarized neural network using diode arrays that efficiently performs vector-matrix multiplication with high accuracy and low energy consumption.

## Contribution

The novel contribution is the development of a diode array-based binarized neural network with self-rectifying and linear characteristics for efficient computation.

## Key findings

- Diode arrays with positive-feedback loops enable efficient vector-matrix multiplication with high linearity.
- The diode arrays demonstrate disturbance-free readout and semi-permanent data retention, suitable for BNN implementation.
- A 2×2 diode array successfully performs matrix multiply-accumulate operations with high concordance to theoretical results.

## Abstract

In this study, a binarized neural network (BNN) of silicon diode arrays achieved vector–matrix multiplication (VMM) between the binarized weights and inputs in these arrays. The diodes that operate in a positive-feedback loop in their p+-n-p-n+ device structure possess steep switching and bistable characteristics with an extremely low subthreshold swing (below 1 mV) and a high current ratio (approximately 108). Moreover, the arrays show a self-rectifying functionality and an outstanding linearity by an R-squared value of 0.99986, which allows to compose a synaptic cell with a single diode. A 2 × 2 diode array can perform matrix multiply-accumulate operations for various binarized weight matrix cases with some input vectors, which is in high concordance with the VMM, owing to the high reliability and uniformity of the diodes. Moreover, the disturbance-free, nondestructive readout, and semi-permanent holding characteristics of the diode arrays support the feasibility of implementing the BNN.