An Online Algorithm for Learning Selectivity to Mixture Means
This work addresses a foundational problem in neural computation and machine learning by offering a biologically-inspired method for unsupervised learning, though it appears incremental as it builds on classical BCM.
The paper tackles the problem of learning class means from mixture models by developing Triplet BCM, a biologically-plausible rule that generalizes classical BCM and provably converges to these means, providing a novel interpretation of BCM as tensor decomposition.
We develop a biologically-plausible learning rule called Triplet BCM that provably converges to the class means of general mixture models. This rule generalizes the classical BCM neural rule, and provides a novel interpretation of classical BCM as performing a kind of tensor decomposition. It achieves a substantial generalization over classical BCM by incorporating triplets of samples from the mixtures, which provides a novel information processing interpretation to spike-timing-dependent plasticity. We provide complete proofs of convergence of this learning rule, and an extended discussion of the connection between BCM and tensor learning.