Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Losses

TL;DR

Forward Target Propagation (FTP) offers a biologically plausible, efficient alternative to backpropagation by replacing the backward pass with a second forward pass, enabling local learning and hardware-friendly neural network training.

Contribution

FTP introduces a forward-only learning algorithm that estimates layerwise targets without symmetric weights or inverse functions, improving biological plausibility and hardware efficiency.

Findings

FTP achieves competitive accuracy on MNIST, CIFAR10, and CIFAR100.

FTP outperforms backpropagation under low-precision hardware constraints.

FTP demonstrates efficiency gains over other biologically inspired learning methods.

Abstract

Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, suffers from key limitations in both biological and hardware perspectives. These include backward error propagation by symmetric weights, non-local credit assignment, and frozen activity during backward passes. We propose Forward Target Propagation (FTP), a biologically plausible and computationally efficient alternative that replaces the backward pass with a second forward pass. FTP estimates layerwise targets using only feedforward computations, eliminating the need for symmetric feedback weights or learnable inverse functions, hence enabling modular and local learning. We evaluate FTP on fully connected networks, CNNs, and RNNs, demonstrating accuracies competitive with BP on MNIST, CIFAR10, and CIFAR100, as well as effective modeling of long-term dependencies in sequential tasks. Moreover, FTP outperforms BP under quantized low-precision and emerging hardware constraints while also demonstrating substantial efficiency gains over other biologically inspired methods such as target propagation variants and forward-only learning algorithms. With its minimal computational overhead, forward-only nature, and hardware compatibility, FTP provides a promising direction for energy-efficient on-device learning and neuromorphic computing.