# Performance evaluation of coherent Ising machines against classical neural networks

## TL;DR

This paper compares the computational performance of coherent Ising machines and classical neural networks, highlighting their similarities and differences in solving combinatorial optimization problems.

## Contribution

It provides a comparative analysis of coherent Ising machines and classical neural networks, focusing on their efficiency in optimization tasks.

## Key findings

- Coherent Ising machines can find near-optimal solutions efficiently.
- Classical neural networks show comparable performance in similar tasks.
- The study highlights the mathematical similarities between the models.

## Abstract

The coherent Ising machine is expected to find a near-optimal solution in various combinatorial optimization problems, which has been experimentally confirmed with optical parametric oscillators (OPOs) and a field programmable gate array (FPGA) circuit. The similar mathematical models were proposed three decades ago by J. J. Hopfield, et al. in the context of classical neural networks. In this article, we compare the computational performance of both models.