Web: http://arxiv.org/abs/2303.07987

March 15, 2023, 1:10 a.m. | Haozhe Jiang, Kaiyue Wen, Yilei Chen

cs.CR updates on arXiv.org arxiv.org

We conduct a systematic study of solving the learning parity with noise
problem (LPN) using neural networks. Our main contribution is designing
families of two-layer neural networks that practically outperform classical
algorithms in high-noise, low-dimension regimes. We consider three settings
where the numbers of LPN samples are abundant, very limited, and in between. In
each setting we provide neural network models that solve LPN as fast as
possible. For some settings we are also able to provide theories that explain …

high networks neural networks

More from arxiv.org / cs.CR updates on arXiv.org

Consultant(e) réseau / sécurité H/F - Innovative Tech

@ Devoteam | Nantes, France

DevSecOps Security Consultant 2023 ECL

@ Bosch Group | Bengaluru, India

Staff Back-end Engineer [Security Architecture & Engineering]

@ Coupang | Seoul, South Korea

Systems Security Engineer

@ Experian | Cyberjaya, Malaysia

Regulatory Compliance Engineer

@ Identiv | Santa Ana, California, United States

Firewall Deployment Engineer

@ Fivesky | Mumbai, IND

Absolvent / Einstieg als Junior IT Consultant für den Bereich IT Security Management (m/w/d)

@ MVI Group GmbH | München, Germany

Analyste de risques/GRC F/H

@ CS GROUP | Le Plessis-Robinson, France

Network Threat Analyst

@ Wyetech | Annapolis Junction, Maryland

Security Engineer - Insider Threat

@ Anduril Industries | Costa Mesa, CA

Data Security Engineer

@ Box | Warsaw, Poland

Zero Trust Solutions Engineer

@ Cloudflare, Inc. | Remote Sweden