QuantumComputingInfo
Researchvia arXiv quant-ph

EPIC-CIM: Training Convolutional Neural Networks on a Coherent Ising Machine via Equilibrium Propagation

arXiv:2607.16271v1 Announce Type: new Abstract: Quantum convolutional neural networks, due to the involvement of quantum measurements and discrete quantum state...

Quantum Editorial Team
July 21, 2026
1 min read
This article has been aggregated from arXiv quant-ph. You can read the original publication at https://arxiv.org/abs/2607.16271.
AI Insights

Get a 3-second summary of this article

EPIC-CIM: Training Convolutional Neural Networks on a Coherent Ising Machine via Equilibrium Propagation

Source: Originally published on arXiv quant-ph on July 21, 2026.

arXiv:2607.16271v1 Announce Type: new Abstract: Quantum convolutional neural networks, due to the involvement of quantum measurements and discrete quantum state evolution, face inherent training challenges associated with non-differentiable operations and discrete optimization dynamics, which make conventional gradient-based learning difficult to apply effectively. In this context, energy-based learning provides a promising alternative by reformulating network training as an energy minimization process without explicit gradient backpropagation.In this framework, input data are processed through convolutional operations, followed by quantum sampling to generate intermediate binary representations, while the output layer also relies on quantum sampling to produce final predictions. The overa...


To read the full article, visit the original source page:

Read the full article on arXiv quant-ph →

#research

Comments are not configured yet. Set up Giscus environment variables to enable discussions.

Required: NEXT_PUBLIC_GISCUS_REPO, NEXT_PUBLIC_GISCUS_REPO_ID, NEXT_PUBLIC_GISCUS_CATEGORY, NEXT_PUBLIC_GISCUS_CATEGORY_ID

Related Articles

HX
Research

A Quantum Reservoir for Neurodynamical Forecasting

arXiv:2608.00139v1 Announce Type: new Abstract: Forecasting neural activity from short recordings remains a fundamental challenge. Reservoir computing may offer...

Aug 4, 20261 min
via arXiv quant-ph
HX
Research

Canonical quantization of the Pais-Uhlenbeck oscillator with a higher-derivative perturbation: a covariant phase space approach

arXiv:2608.00108v1 Announce Type: new Abstract: In this paper, we apply the covariant phase space formalism to the perturbative canonical quantization of the Pa...

Aug 4, 20261 min
via arXiv quant-ph
Research

Exact minimum measurement dependence for faithful local deterministic models of multipartite GHZ-Mermin correlations

arXiv:2608.00124v1 Announce Type: new Abstract: Bell derivations rest on locality, determinism, and measurement independence. Hall [Phys. Rev. Lett. 105, 250404...

Aug 4, 20261 min
via arXiv quant-ph