无需反向传播即可稳定训练神经网络，实现物理系统中的原位学习。
Local learning for stable backpropagation-free neural network training towards physical learning
- 采用逐层局部学习与前向评估优化，摆脱反向传播依赖。
- 在模拟光子网络中实现多层感知机与卷积网络的稳定训练。
- 适合追求低功耗、物理可集成神经网络的科研与工程应用。
尽管反向传播和自动微分推动了深度学习的发展，但芯片制造的物理极限及深度学习日益增长的环境成本，促使人们探索替代学习范式，如物理神经网络。然而，大多数现有物理神经网络仍依赖数字计算进行训练，因为反向传播和自动微分难以在物理系统中实现。本文提出FFzero，一种仅通过前向计算实现稳定神经网络训练的前向学习框架。该框架结合逐层局部学习、基于原型的表示以及基于方向导数的优化，仅依赖前向评估完成训练。我们证明，在仅允许前向优化的情况下，局部学习有效而反向传播失效。FFzero可泛化至多层感知机与卷积神经网络，适用于分类与回归任务。以模拟光子神经网络为例，验证了其在无反向传播条件下实现原位物理学习的可行性。
原文摘要 · Abstract (English)
While backpropagation and automatic differentiation have driven deep learning's success, the physical limits of chip manufacturing and rising environmental costs of deep learning motivate alternative learning paradigms such as physical neural networks. However, most existing physical neural networks still rely on digital computing for training, largely because backpropagation and automatic differentiation are difficult to realize in physical systems. We introduce FFzero, a forward-only learning framework enabling stable neural network training without backpropagation or automatic differentiation. FFzero combines layer-wise local learning, prototype-based representations, and directional-derivative-based optimization through forward evaluations only. We show that local learning is effective under forward-only optimization, where backpropagation fails. FFzero generalizes to multilayer perceptron and convolutional neural networks across classification and regression. Using a simulated photonic neural network as an example, we demonstrate that FFzero provides a viable path toward backpropagation-free in-situ physical learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。