PulseAugur
EN
LIVE 06:45:14

Physical noise in quantum neural networks explored as a native regularizer

By PulseAugur Editorial · [1 sources] ·

Researchers have explored the potential of using physical noise in photonic hybrid quantum neural networks (PHQNNs) as a native regularizer, drawing parallels to noise-injection techniques in classical deep learning. By employing a genetic algorithm to tune noise parameters within Quandela's Perceval simulator and the MerLin framework, the study aimed to optimize PHQCNN performance on datasets like Iris, Digits, and MNIST. While this approach yielded modest accuracy gains on Iris and Digits, it resulted in a degradation of performance on MNIST, indicating that the beneficial effects of physical noise as a regularizer are dataset-dependent. AI

IMPACT This research explores a novel method for improving quantum neural network performance by leveraging inherent physical noise, potentially offering a new avenue for regularization in quantum computing.

RANK_REASON Research paper detailing a novel approach to quantum neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Physical noise in quantum neural networks explored as a native regularizer

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Farah Elnakhal, Alberto Marchisio, Nouhaila Innan, Gabriel Falcao, Muhammad Shafique ·

    PN-QNN: Harnessing Physical Noise as a Native Regularizer in Photonic Hybrid Quantum Neural Networks

    arXiv:2607.20045v1 Announce Type: cross Abstract: Physical noise in near-term quantum hardware is usually treated as a nuisance to suppress. We ask whether it can instead act as a hardware-native regularizer for photonic hybrid quantum-classical neural networks (PHQCNNs), analogo…

RELATED ENTITIES

RELATED TOPICS