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

arXiv:2506.11030 · cs.LG, cs.AI · Submitted 2025-05-20 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-05-20

Updated: 2026-10-01

Code: https://github.com/mlcommons/tiny

Terminology

• Credit assignment — 2× in this paper · explained in 3 episodes
• Forward Target Propagation — 2× in this paper
• Computational overhead — 1× in this paper · explained in 2 episodes

Sources

• How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation
• Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition
• The Forward-Forward Algorithm: Some Preliminary Investigations
• Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
• Error Forward-Propagation: Reusing Feedforward Connections to Propagate Errors in Deep Learning
• Dendritic Localized Learning: Toward Biologically Plausible Algorithm
• Predictive Coding: a Theoretical and Experimental Review
• The Predictive Forward-Forward Algorithm
• Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks