paper-with-me

홈 › Papers

Boolean learning under noise-perturbations in hardware neural networks

2020-03-27 · Louis Andreoli, Xavier Porte, Stéphane Chrétien, Maxime Jacquot, Laurent Larger, Daniel Brunner

A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems have recently implemented some or all of these operations, yet the focus was placed on addressing technological challenges. Fundamental questions regarding learning in hardware neural networks remain largely unexplored. Noise in particular is unavoidable in such architectures, and here we investigate its interaction with a learning algorithm using an opto-electronic recurrent neural network. We find that noise strongly modifies the system's path during convergence, and surprisingly fully decorrelates the final readout weight matrices. This highlights the importance of understanding architecture, noise and learning algorithm as interacting players, and therefore identifies the need for mathematical tools for noisy, analogue system optimization.

📄 PDF Abstract BibTeX arXiv:2003.12319

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Attractor Stability of Boolean networks under noise

2025-06-18 · Byungjoon Min, Jeehye Choi, Reinhard Laubenbacher

We study the impact of noise on attractor dynamics in Boolean networks, focusing on their stability and transition behaviors. By constructing attractor matrices based on single-node perturbations, we propose a framework …

Curved Boolean Logic: A Contextual Generalization of Propositional Logic with Algorithmic Consequences

2025-10-06 · Maximilian R. P. von Liechtenstein arxiv

Curved Boolean Logic (CBL) generalizes propositional logic by allowing local truth assignments that do not extend to a single global valuation, analogous to curvature in geometry. We give equivalent sheaf and exclusivity…

Attacking Deep Learning AI Hardware with Universal Adversarial Perturbation

2021-11-18 · Mehdi Sadi, B. M. S. Bahar Talukder, Kaniz Mishty, Md Tauhidur Rahman

Universal Adversarial Perturbations are image-agnostic and model-independent noise that when added with any image can mislead the trained Deep Convolutional Neural Networks into the wrong prediction. Since these Universa…

Deep Learning

A Dynamics-based Approach for the Target Control of Boolean Networks

2020-06-03 · Cui Su, Jun Pang

We study the target control problem of asynchronous Boolean networks, to identify a set of nodes, the perturbation of which can drive the dynamics of the network from any initial state to the desired steady state (or att…

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

2026-07-22 · Farah Elnakhal, Alberto Marchisio, Nouhaila Innan, Gabriel Falcao 외 arxiv

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…