Newest papers

Forward-Only Learning for Shared-Kernel Wavelet Neural Networks without Backpropagation

Yongfei Guo, Xuan Sun, Ang Li, Zhao Zhang, Yuanhao Gong · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29697 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

وبالرغم من أن التقويم المستمر يمنع التقويم المستقبلي، إلا أنه يستخدم التقويم المستقبلي والتحديثات المحلية التي يمكن أن تتعرض لخسارة أو انفجار التقويم في الشبكات العميقة. على الرغم من أن التقويم المستقبلي يمنع التقويم المستقبلي، إلا أنه لا يزال أساساً على المستوى المحلي أو القاعدي، مما يؤدي إلى تعزيز التعلم العالمي على الشبكة بأكملها باستخدام التقييمات المستقبلية فقط. لذلك، فإننا نقدم إطار تعلم المستقبلي العالمي على أساس CMA-ES. ونحن نقدم أيضا تقويم تقويم المستقبلي على أساس البنية التحتية وتقسيم القيمة القيمة القيمة القيمة القيمة القيمة القيمة القيمة القيمة القيمة القيمة القيمة القيمة

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

Abstract

Backpropagation remains the dominant training paradigm, using backward gradients and local updates that can suffer from vanishing or exploding gradients in deep networks. Although the Forward-Forward algorithm avoids conventional backpropagation, it remains mainly local or layer-wise, motivating global whole-network learning using forward evaluations only. For shared-kernel wavelet neural networks, we therefore propose a CMA-ES-based global forward-only learning framework. We further introduce structure-aware parameter decomposition and channel-specific credit assignment, factorizing the search into three subspaces. On BSDS500, our method reduces test MSE from 4.1783 to 4.0130 and improves PSNR from 42.621 to 42.787~dB over Adam/BP without backward propagation. Beyond these gains, training requires only 6 training-set coverages, compared with 1500 epochs for BP. Ablations show that structural decomposition and aligned credit assignment are more important than increasing population size, demonstrating the feasibility of whole-network forward-only learning for compact reconstruction networks. These results suggest a potential route toward forward-only optimization of compact reconstruction models for resource-constrained imaging and edge or near-sensor systems.

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

Topics: Backpropagation, Artificial intelligence, Artificial neural network, Computer science, Wavelet, Pattern recognition (psychology)

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=2610.29697, 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