mlsanityData to 14 Oct 2026

A Normative and Biologically Plausible Algorithm for Independent Component Analysis

arXiv 2111.08858 ↗First posted 17 Nov 2021cs.NE cs.AI q-bio.NCcited by 8

Not on the map. Why?

Abstract (arXiv)

The brain effortlessly solves blind source separation (BSS) problems, but the algorithm it uses remains elusive. In signal processing, linear BSS problems are often solved by Independent Component Analysis (ICA). To serve as a model of a biological circuit, the ICA neural network (NN) must satisfy at least the following requirements: 1. The algorithm must operate in the online setting where data samples are streamed one at a time, and the NN computes the sources on the fly without storing any significant fraction of the data in memory. 2. The synaptic weight update is local, i.e., it depends only on the biophysical variables present in the vicinity of a synapse. Here, we propose a novel objective function for ICA from which we derive a biologically plausible NN, including both the neural architecture and the synaptic learning rules. Interestingly, our algorithm relies on modulating synaptic plasticity by the total activity of the output neurons. In the brain, this could be accomplished by neuromodulators, extracellular calcium, local field potential, or nitric oxide.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 23 of its 129 references that are in the map. First posted on arXiv 17 Nov 2021.

Builds on

23 of 129 references.

References · 23

  1. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  2. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 282
  3. 2018Dendritic cortical microcircuits approximate the backpropagation algorithmcited by 97
  4. 2016Towards deep learning with segregated dendritescited by 71
  5. 2017Learning Independent Features with Adversarial Nets for Non-linear ICAcited by 33
  6. 2015A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Datacited by 26
  7. 2017Why do similarity matching objectives lead to Hebbian/anti-Hebbian networks?cited by 20
  8. 2019Neuroscience-inspired online unsupervised learning algorithmscited by 19
  9. 2021Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networkscited by 15
  10. 2015A Normative Theory of Adaptive Dimensionality Reduction in Neural Networkscited by 12
  11. 2017The brain as an efficient and robust adaptive learnercited by 11
  12. 2017Blind nonnegative source separation using biological neural networkscited by 11
11 more
  1. 2015A Hebbian/Anti-Hebbian Network Derived from Online Non-Negative Matrix Factorization Can Cluster and Discover Sparse Featurescited by 10
  2. 2020A biologically plausible neural network for multi-channel Canonical Correlation Analysiscited by 9
  3. 2020A biologically plausible neural network for Slow Feature Analysiscited by 8
  4. 2017Learning to represent signals spike by spikecited by 6
  5. 2020A simple normative network approximates local non-Hebbian learning in the cortexcited by 6
  6. 2018Biologically Plausible Online Principal Component Analysis Without Recurrent Neural Dynamicscited by 4
  7. 2019A Spiking Neural Network with Local Learning Rules Derived From Nonnegative Similarity Matchingcited by 4
  8. 2020Blind Bounded Source Separation Using Neural Networks with Local Learning Rulescited by 4
  9. 2021A Similarity-preserving Neural Network Trained on Transformed Images Recapitulates Salient Features of the Fly Motion Detection Circuitcited by 3
  10. 2018Multi-set Canonical Correlation Analysis simply explainedcited by 1
  11. 2021A Neural Network with Local Learning Rules for Minor Subspace Analysiscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 0; 2025: 1; 2026: 2.

8 papers.

  1. 2022Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sourcescited by 6
  2. 2023Normative framework for deriving neural networks with multi-compartmental neurons and non-Hebbian plasticitycited by 4
  3. 2022Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rulescited by 3
  4. 2022Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separationcited by 3
  5. 2023Duality Principle and Biologically Plausible Learning: Connecting the Representer Theorem and Hebbian Learningcited by 2
  6. 2025Unsupervised Learning in Echo State Networks for Input Reconstructioncited by 1
  7. 2026Normative Networks for Source Separation via Local Plasticity and Dendritic Computationcited by 0
  8. 2026Flexible Online Representation Learning Based on Similarity Matchingcited by 0