mlsanityData to 14 Oct 2026

Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways

arXiv 2210.16414 ↗First posted 28 Oct 2022q-bio.NC cs.LG cs.NEcited by 14

Not on the map. Why?

Abstract (arXiv)

Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback projections that are symmetric with feedforward connections, but experiments do not corroborate the existence of such symmetric backward connectivity. Random feedback alignment offers an alternative model in which errors are propagated backward through fixed, random backward connections. This approach successfully trains shallow models, but learns slowly and does not perform well with deeper models or online learning. In this study, we develop a meta-learning approach to discover interpretable, biologically plausible plasticity rules that improve online learning performance with fixed random feedback connections. The resulting plasticity rules show improved online training of deep models in the low data regime. Our results highlight the potential of meta-learning to discover effective, interpretable learning rules satisfying biological constraints.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 20 of its 61 references that are in the map. First posted on arXiv 28 Oct 2022.

Builds on

20 of 61 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2016Learning to learn by gradient descent by gradient descentcited by 620
  6. 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
  7. 2019Meta-Learning Representations for Continual Learningcited by 189
  8. 2018Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architecturescited by 101
  9. 2018Dendritic cortical microcircuits approximate the backpropagation algorithmcited by 97
  10. 2019Deep Learning without Weight Transportcited by 87
  11. 2018Differentiable plasticity: training plastic neural networks with backpropagationcited by 84
  12. 2015How Important is Weight Symmetry in Backpropagation?cited by 58
8 more
  1. 2020Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticitycited by 41
  2. 2018Meta-Learning Update Rules for Unsupervised Representation Learningcited by 37
  3. 2019Learning to solve the credit assignment problemcited by 27
  4. 2020Two Routes to Scalable Credit Assignment without Weight Symmetrycited by 19
  5. 2018Deep learning with asymmetric connections and Hebbian updatescited by 16
  6. 2020Learning to Learn with Feedback and Local Plasticitycited by 11
  7. 2019Spike-based causal inference for weight alignmentcited by 10
  8. 2021Meta-Learning Bidirectional Update Rulescited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 6; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluationcited by 8
  2. 2024Pretraining with Random Noise for Fast and Robust Learning without Weight Transportcited by 5
  3. 2025Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stabilitycited by 5
  4. 2026Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognitioncited by 3
  5. 2024Deep Learning without Weight Symmetrycited by 1
  6. 2024Oja's plasticity rule overcomes several challenges of training neural networks under biological constraintscited by 1
  7. 2024Skewed Neuronal Heterogeneity Enhances Efficiency On Various Computing Systemscited by 0
  8. 2025Can Local Representation Alignment RNNs Solve Temporal Tasks?cited by 0
  9. 2025Forward Target Propagation: A Forward-Only Approach to Global Error Credit Assignment via Local Lossescited by 0
  10. 2025Eigen Neural Network: Unlocking Generalizable Vision with Eigenbasiscited by 0
  11. 2025Flexible inference for animal learning rules using neural networkscited by 0
  12. 2025Meta-learning three-factor plasticity rules for structured credit assignment with sparse feedbackcited by 0
2 more
  1. 2026Hierarchical Zero-Order Optimization for Deep Neural Networkscited by 0
  2. 2026Online Task Adaptation via Self-Organisationcited by 0