A biologically plausible neural network for multi-channel Canonical Correlation Analysis
This work addresses the challenge of aligning computational methods with biological constraints for neuroscience and AI, though it is incremental as it adapts existing CCA concepts to a neural network context.
The authors tackled the problem of implementing Canonical Correlation Analysis (CCA) in a biologically plausible neural network by deriving an online algorithm with local synaptic update rules, resulting in a single-layer network with multi-compartmental neurons that mimics cortical circuitry.
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.