# Optical Full Adder Based on Integrated Diffractive Neural Network

## TL;DR

This paper introduces an on-chip optical full adder using a diffractive neural network for high-speed, accurate parallel logic operations.

## Contribution

The novel approach uses a diffractive neural network with quantum dot-based nonlinearity for precise optical computing.

## Key findings

- A 4-bit on-chip D2NN full adder was designed and demonstrated.
- The proposed architecture achieved 100% accuracy in simulations for 4-bit full adders.
- Quantum dots were used to mimic the tanh function for nonlinear optical computing.

## Abstract

Light has been intensively investigated as a computing medium due to its high-speed propagation and large operation bandwidth. Since the invention of the first laser in 1960, the development of optical computing technologies has presented both challenges and opportunities. Recent advances in artificial intelligence over the past decade have opened up new horizons for optical computing applications. This study presents an end-to-end truth table direct mapping approach using on-chip deep diffractive neural network (D2NN) technology to achieve highly parallel optical logic operations. To enable precise logical operations, we propose an on-chip nonlinear solution leveraging the similarity between the hyperbolic tangent (tanh) function and reverse saturable absorption characteristics of quantum dots. We design and demonstrate a 4-bit on-chip D2NN full adder circuit. The simulation results show that the proposed architecture achieves 100% accuracy for 4-bit full adders across the entire dataset.