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

Korean

Backpropagation은 지배적 인 훈련 패러다임을 유지하며, 뒤로 가는 gradients와 깊은 네트워크에서 사라지거나 폭발하는 gradients로 고통받을 수있는 로컬 업데이트를 사용합니다. Backpropagation은 전통적인 backpropagation을 피하는 반면, 그것은 주로 로컬 또는 레이어 방향으로 남아 있으며, 전 세계 전체 네트워크 학습을 단지 앞으로 평가를 사용하여 동기를 부여합니다. 공유 코어 wavelet 신경 네트워크의 경우, 우리는 CMA-ES 기반 글로벌 forward-only 학습 프레임 워크를 제안합니다. 우리는 구조-aware 매개 변수 분해 및 채널 특정 크레딧 할당을 추가합니다. BSDS500에서 우리의 방법은 MSE를 4.1783에서 4.0130로 감소시키고

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)

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