Local learning for stable backpropagation-free neural network training towards physical learning
This work addresses the problem of enabling efficient and environmentally sustainable neural network training for physical systems, representing an incremental advancement in alternative learning paradigms.
The paper tackles the challenge of training neural networks without backpropagation, which is difficult in physical systems, by introducing FFzero, a forward-only learning framework that enables stable training and generalizes to various network types and tasks.
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.