Yongfei Guo, Xuan Sun, Ang Li, Zhao Zhang, Yuanhao Gong · 2026 · arXiv
DOI: 10.48550/arXiv.2610.29697 · open-access PDF
Backpropagation bleibt das dominante Trainingsparadigma, wobei rückwärtige Gradienten und lokale Updates verwendet werden, die durch verschwindende oder explodierende Gradienten in tiefen Netzwerken betroffen sein können. Obwohl der Forward-Forward-Algorithmus konventionelle Backpropagation vermeidet, bleibt er hauptsächlich lokal oder schichtweise, wodurch globales Ganznetz-Lernen nur mit vorwärtigen Bewertungen motiviert wird.Für gemeinsame Kernel-Wavelet-Nervennetzwerke schlagen wir daher einen CMA-ES-basierten globalen forward-only-Learning-Framework vor.
Machine translation (Meta M2M100); the English original follows.
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 searc
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange