Newest papers

The role of locality and weight sharing in convolutional neural networks

Francesco Mori, Melanie Weber · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30118 · open-access PDF

Arabic

ومع ذلك، كيف يتم تشكيل هذه الخصائص اثنين من التعلم بشكل منفصل، وكيف تعتمد آثارها على التوازن الفردي من الصور الطبيعية، لا تزال معقدة. نحن نناقش هذه الأسئلة في نموذج المعلم-الطلاب مع معلم التوازن يعمل على منصات الدخول $P$ مع التوازن $c$ بين منصات. نحن مقارنة الطلاب التوازن والمرابطين المحليين الذين تم تدريبهم من خلال الانترنت التراجع الصلب السكاني، وتتلقى التوازنات التفاعلية العادية التي تعبر ديناميكيةهم بشكل صحيح في t

Machine translation (Meta M2M100); the English original follows.

Abstract

The success of convolutional neural networks is often attributed to locality and weight sharing. However, how these two properties separately shape learning, and how their effects depend on the spatial correlations of natural images, remain poorly understood. We address these questions in a teacher-student model with a convolutional teacher acting on $P$ input positions with correlation $c$ between positions. We compare convolutional and locally connected students trained by online stochastic gradient descent, and derive ordinary differential equations that describe their dynamics exactly in t

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30118, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange