mlsanityData to 7 Oct 2026

Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment

arXiv 2312.09257 ↗First posted 1 Dec 2023cs.NE cs.LG q-bio.NCcited by 13

Not on the map. Why?

Abstract (arXiv)

In this survey, we examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology. These processes are unified under one possible taxonomy, which is constructed based on how a learning algorithm answers a central question underpinning the mechanisms of synaptic plasticity in complex adaptive neuronal systems: where do the signals that drive the learning in individual elements of a network come from and how are they produced? In this unified treatment, we organize the ever-growing set of brain-inspired learning schemes into six general families and consider these in the context of backpropagation of errors and its known criticisms. The results of this review are meant to encourage future developments in neuro-mimetic systems and their constituent learning processes, wherein lies an important opportunity to build a strong bridge between machine learning, computational neuroscience, and cognitive science.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 82 of its 480 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

82 of 480 references.

References · 82

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Layer Normalizationcited by 5,579
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  5. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  6. 2020Hopfield Networks is All You Needcited by 461
  7. 2014Deeply-Supervised Netscited by 364
  8. 2022The Forward-Forward Algorithm: Some Preliminary Investigationscited by 262
  9. 2016Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagationcited by 251
  10. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 203
  11. 2016Decoupled Neural Interfaces using Synthetic Gradientscited by 135
  12. 2020Predictive Coding Approximates Backprop along Arbitrary Computation Graphscited by 89
38 more
  1. 2019Deep Learning without Weight Transportcited by 87
  2. 2014How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagationcited by 77
  3. 2020Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networkscited by 73
  4. 2021Revisiting Locally Supervised Learning: an Alternative to End-to-end Trainingcited by 71
  5. 2018Reviving and Improving Recurrent Back-Propagationcited by 69
  6. 2017On weight initialization in deep neural networkscited by 67
  7. 2014Reweighted Wake-Sleepcited by 66
  8. 2015Towards Biologically Plausible Deep Learningcited by 66
  9. 2022Scaling Forward Gradient With Local Lossescited by 65
  10. 2022Hebbian Deep Learning Without Feedbackcited by 61
  11. 2020Training End-to-End Analog Neural Networks with Equilibrium Propagationcited by 57
  12. 2017Unbiased Online Recurrent Optimizationcited by 46
  13. 2018Unsupervised Learning by Competing Hidden Unitscited by 44
  14. 2016Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortexcited by 42
  15. 2018Biologically-plausible learning algorithms can scale to large datasetscited by 37
  16. 2023The Predictive Forward-Forward Algorithmcited by 35
  17. 2017Equivalence of Equilibrium Propagation and Recurrent Backpropagationcited by 31
  18. 2018Feedback alignment in deep convolutional networkscited by 31
  19. 2023Brain-inspired Computational Intelligence via Predictive Codingcited by 30
  20. 2018Approximating Real-Time Recurrent Learning with Random Kronecker Factorscited by 29
  21. 2019Learning to solve the credit assignment problemcited by 27
  22. 2023SymBa: Symmetric Backpropagation-Free Contrastive Learning with Forward-Forward Algorithm for Optimizing Convergencecited by 27
  23. 2018Deep Predictive Coding Network for Object Recognitioncited by 23
  24. 2019Principled Training of Neural Networks with Direct Feedback Alignmentcited by 23
  25. 2023Blockwise Self-Supervised Learning at Scalecited by 22
  26. 2018Generalization of Equilibrium Propagation to Vector Field Dynamicscited by 21
  27. 2022A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networkscited by 21
  28. 2016Reinforcement Learning Using Quantum Boltzmann Machinescited by 19
  29. 2023Forward-Forward Training of an Optical Neural Networkcited by 19
  30. 2023The Cascaded Forward Algorithm for Neural Network Trainingcited by 17
  31. 2018Error Forward-Propagation: Reusing Feedforward Connections to Propagate Errors in Deep Learningcited by 16
  32. 2019Local Unsupervised Learning for Image Analysiscited by 16
  33. 2020Deriving Differential Target Propagation from Iterating Approximate Inversescited by 15
  34. 2013Deep Predictive Coding Networkscited by 13
  35. 2015Early Inference in Energy-Based Models Approximates Back-Propagationcited by 13
  36. 2017Learning to Adapt by Minimizing Discrepancycited by 12
  37. 2018Conducting Credit Assignment by Aligning Local Representationscited by 12
  38. 2022Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Againcited by 11

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 4.

13 papers.

Sort:

  1. 2025Stochastic Forward-Forward Learning through Representational Dimensionality Compressioncited by 4
  2. 2024Temporal-Difference Learning Using Distributed Error Signalscited by 3
  3. 2024A Contrastive Symmetric Forward-Forward Algorithm (SFFA) for Continual Learning Taskscited by 2
  4. 2025Toward Practical Equilibrium Propagation: Brain-inspired Recurrent Neural Network with Feedback Regulation and Residual Connectionscited by 2
  5. 2026Accelerated Predictive Coding Networks via Direct Kolen-Pollack Feedback Alignmentcited by 2
  6. 2024Neuro-mimetic Task-free Unsupervised Online Learning with Continual Self-Organizing Mapscited by 1
  7. 2024Forward Learning of Graph Neural Networkscited by 1
  8. 2024Emerging NeoHebbian Dynamics in Forward-Forward Learning: Implications for Neuromorphic Computingcited by 1
  9. 2024On the Improvement of Generalization and Stability of Forward-Only Learning via Neural Polarizationcited by 1
  10. 2026HCL-FF: Hierarchical and Contrastive Learning for Forward-Forward Algorithmcited by 1
  11. 2025Meta-Representational Predictive Coding: Neuroscience-Informed Self-Supervised Learningcited by 0
  12. 2026Hebbian Learning with Global Directioncited by 0
1 more
  1. 2026Error Highways: Scaling Predictive Coding to Very Deep Networkscited by 0