mlsanityData to 13 Oct 2026

Unsupervised Learning by Competing Hidden Units

arXiv 1806.10181 ↗First posted 26 Jun 2018cs.LG cs.CV cs.NEcited by 44

Not on the map. Why?

Abstract (arXiv)

It is widely believed that the backpropagation algorithm is essential for learning good feature detectors in early layers of artificial neural networks, so that these detectors are useful for the task performed by the higher layers of that neural network. At the same time, the traditional form of backpropagation is biologically implausible. In the present paper we propose an unusual learning rule, which has a degree of biological plausibility, and which is motivated by Hebb's idea that change of the synapse strength should be local - i.e. should depend only on the activities of the pre and post synaptic neurons. We design a learning algorithm that utilizes global inhibition in the hidden layer, and is capable of learning early feature detectors in a completely unsupervised way. These learned lower layer feature detectors can be used to train higher layer weights in a usual supervised way so that the performance of the full network is comparable to the performance of standard feedforward networks trained end-to-end with a backpropagation algorithm.

Key facts. Cited by 44 papers in the map (data through 13 Oct 2026). First posted on arXiv 26 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 9; 2024: 4; 2025: 5; 2026: 7.

44 papers.

Sort:

  1. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 127
  2. 2022Hebbian Deep Learning Without Feedbackcited by 61
  3. 2021Associative Memories via Predictive Codingcited by 43
  4. 2021SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networkscited by 30
  5. 2023Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptationcited by 23
  6. 2021Hebbian Semi-Supervised Learning in a Sample Efficiency Settingcited by 19
  7. 2021Can a Fruit Fly Learn Word Embeddings?cited by 17
  8. 2024Self-Contrastive Forward-Forward Algorithmcited by 16
  9. 2023Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignmentcited by 14
  10. 2022FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Levelcited by 11
  11. 2023Sparse Distributed Memory is a Continual Learnercited by 11
  12. 2022Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backpropcited by 9
32 more
  1. 2023Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Surveycited by 8
  2. 2023Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Surveycited by 7
  3. 2022Activation Learning by Local Competitionscited by 6
  4. 2021Training Deep Architectures Without End-to-End Backpropagation: A Survey on the Provably Optimal Methodscited by 5
  5. 2023Machine learning in and out of equilibriumcited by 5
  6. 2024Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imagingcited by 4
  7. 2025Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networkscited by 4
  8. 2021Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detectioncited by 3
  9. 2022Unsupervised Hebbian Learning on Point Sets in StarCraft IIcited by 3
  10. 2021PyTorch-Hebbian: facilitating local learning in a deep learning frameworkcited by 2
  11. 2023Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learningcited by 2
  12. 2025OscNet: Machine Learning on CMOS Oscillator Networkscited by 2
  13. 2025From Neurons to Computation: Biological Reservoir Computing for Pattern Recognitioncited by 2
  14. 2026A feedback control optimizer for online and hardware-aware training of Spiking Neural Networkscited by 2
  15. 2022Revisiting Gaussian Neurons for Online Clustering with Unknown Number of Clusterscited by 1
  16. 2022Hebbian Continual Representation Learningcited by 1
  17. 2022Forecasting Evolution of Clusters in Game Agents with Hebbian Learningcited by 1
  18. 2024Unsupervised End-to-End Training with a Self-Defined Targetcited by 1
  19. 2025From Neural Activity to Computation: Biological Reservoirs for Pattern Recognition in Digit Classificationcited by 1
  20. 2026Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representationscited by 1
  21. 2026Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimizationcited by 1
  22. 2021Feature Alignment as a Generative Processcited by 0
  23. 2021A Biologically Plausible Learning Rule for Perceptual Systems of organisms that Maximize Mutual Informationcited by 0
  24. 2022Multi-level Data Representation For Training Deep Helmholtz Machinescited by 0
  25. 2023Extracting the Brain-like Representation by an Improved Self-Organizing Map for Image Classificationcited by 0
  26. 2023Active Inference in Hebbian Learning Networkscited by 0
  27. 2024Exploring Biologically Inspired Mechanisms of Adversarial Robustnesscited by 0
  28. 2025Comply: Learning Sentences with Complex Weights inspired by Fruit Fly Olfactioncited by 0
  29. 2026Temporal Complexity and Self-Organization in an Exponential Dense Associative Memory Modelcited by 0
  30. 2026Hebbian Learning with Global Directioncited by 0
  31. 2026Self-Organized Learning in Oscillatory Neural Networks with Memristive Signed Couplingscited by 0
  32. 2026Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraintscited by 0