A biologically plausible neural network for multichannel canonical correlation analysis

DOI10.1162/NECO_A_01414MaRDI QIDQ5033519zbMATH OpenOpenAlexFDO

Authors David Lipshutz, Yanis Bahroun, Siavash Golkar, Dmitri B. Chklovskii, Anirvan Sengupta

Publication date 23 February 2022

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2010.00525

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: Cortical pyramidal neurons receive inputs from multiple distinct neural populations and integrate these inputs in separate dendritic compartments. We explore the possibility that cortical microcircuits implement Canonical Correlation Analysis (CCA), an unsupervised learning method that projects the inputs onto a common subspace so as to maximize the correlations between the projections. To this end, we seek a multi-channel CCA algorithm that can be implemented in a biologically plausible neural network. For biological plausibility, we require that the network operates in the online setting and its synaptic update rules are local. Starting from a novel CCA objective function, we derive an online optimization algorithm whose optimization steps can be implemented in a single-layer neural network with multi-compartmental neurons and local non-Hebbian learning rules. We also derive an extension of our online CCA algorithm with adaptive output rank and output whitening. Interestingly, the extension maps onto a neural network whose neural architecture and synaptic updates resemble neural circuitry and synaptic plasticity observed experimentally in cortical pyramidal neurons.

Recommendations

• A learning algorithm for adaptive canonical correlation analysis of several data sets
• Biologically plausible single-layer networks for nonnegative independent component analysis
• A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data
• A family of canonical correlation networks
• Blind nonnegative source separation using biological neural networks

Cites work

• scientific article; zbMATH DE number 5286897 (Why is no real title available?)
• scientific article; zbMATH DE number 5348356 (Why is no real title available?)
• A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data
• A canonical correlation neural network for multicollinearity and functional data
• A learning algorithm for adaptive canonical correlation analysis of several data sets
• A simplified neuron model as a principal component analyzer
• Cycles in adversarial regularized learning
• Multiple equilibria and limit cycles in evolutionary games with logit dynamics
• Multivariate reduced-rank regression
• RELATIONS BETWEEN TWO SETS OF VARIATES
• Stochastic approximation with two time scales
• Supervised and unsupervised learning with two sites of synaptic integration
• Why do similarity matching objectives lead to Hebbian/anti-Hebbian networks?

Cited in

(3)

• Supervised and unsupervised learning with two sites of synaptic integration
• Biologically plausible single-layer networks for nonnegative independent component analysis
• A family of canonical correlation networks

This page was built for publication: A biologically plausible neural network for multichannel canonical correlation analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033519)