mlsanityData to 14 Oct 2026

Biologically Motivated Algorithms for Propagating Local Target Representations

arXiv 1805.11703 ↗First posted 26 May 2018cs.NE cs.LG stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a learning algorithm called error-driven Local Representation Alignment (LRA-E), which has strong connections to predictive coding, a theory that offers a mechanistic way of describing neurocomputational machinery. In addition, we propose an improved variant of Difference Target Propagation, another procedure that comes from the same family of algorithms as LRA-E. We compare our procedures to several other biologically-motivated algorithms, including two feedback alignment algorithms and Equilibrium Propagation. In two benchmarks, we find that both of our proposed algorithms yield stable performance and strong generalization compared to other competing back-propagation alternatives when training deeper, highly nonlinear networks, with LRA-E performing the best overall.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 12; 2023: 10; 2024: 6; 2025: 5; 2026: 2.

43 papers.

Sort:

By area:

  1. 2021Predictive Coding: a Theoretical and Experimental Reviewcited by 77
  2. 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
  3. 2023The Predictive Forward-Forward Algorithmcited by 35
  4. 2022Learning on Arbitrary Graph Topologies via Predictive Codingcited by 33
  5. 2023Brain-inspired Computational Intelligence via Predictive Codingcited by 30
  6. 2022Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learningcited by 26
  7. 2022A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networkscited by 22
  8. 2022A Theoretical Framework for Inference Learningcited by 17
  9. 2023The Cascaded Forward Algorithm for Neural Network Trainingcited by 17
  10. 2021Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networkscited by 14
  11. 2021How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspectivecited by 13
  12. 2023Forward Learning with Top-Down Feedback: Empirical and Analytical Characterizationcited by 13
31 more
  1. 2021Backprop-Free Reinforcement Learning with Active Neural Generative Codingcited by 12
  2. 2022Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Imagescited by 10
  3. 2022Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backpropcited by 9
  4. 2021Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learningcited by 6
  5. 2022Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problemscited by 6
  6. 2022Fixed-Weight Difference Target Propagationcited by 6
  7. 2023Block-local learning with probabilistic latent representationscited by 6
  8. 2023Predictive Coding beyond Correlationscited by 6
  9. 2024A Review of Neuroscience-Inspired Machine Learningcited by 6
  10. 2021Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methodscited by 5
  11. 2021Bilevel Programs Meet Deep Learning: A Unifying View on Inference Learning Methodscited by 5
  12. 2024Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learningcited by 5
  13. 2023A Novel Noise Injection-based Training Scheme for Better Model Robustnesscited by 3
  14. 2023Feed-Forward Optimization With Delayed Feedback for Neural Network Trainingcited by 3
  15. 2024Tight Stability, Convergence, and Robustness Bounds for Predictive Coding Networkscited by 3
  16. 2022An Empirical Analysis of Recurrent Learning Algorithms In Neural Lossy Image Compression Systemscited by 2
  17. 2022A Robust Backpropagation-Free Framework for Imagescited by 2
  18. 2023Duality Principle and Biologically Plausible Learning: Connecting the Representer Theorem and Hebbian Learningcited by 2
  19. 2025Closed-Form Feedback-Free Learning with Forward Projectioncited by 2
  20. 2025Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connectionscited by 2
  21. 2026HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithmcited by 2
  22. 2023Understanding Predictive Coding as an Adaptive Trust-Region Methodcited by 1
  23. 2024Forward Learning of Graph Neural Networkscited by 1
  24. 2024A Unified Framework for Neural Computation and Learning Over Timecited by 1
  25. 2021Front Contribution instead of Back Propagationcited by 0
  26. 2022Physical Deep Learning with Biologically Plausible Training Methodcited by 0
  27. 2024Nature-Inspired Local Propagationcited by 0
  28. 2025Can Local Representation Alignment RNNs Solve Temporal Tasks?cited by 0
  29. 2025Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Lossescited by 0
  30. 2025Local Pairwise Distance Matching for Backpropagation-Free Reinforcement Learningcited by 0
  31. 2026Error Highways: Scaling Predictive Coding to Very Deep Networkscited by 0