Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation
This work addresses a fundamental limitation in neural network models for source separation, offering a more flexible approach for scenarios where latent causes are correlated, though it appears incremental in extending existing methods.
The paper tackled the problem of separating correlated latent sources, which prior methods assumed independence, by proposing a biologically plausible neural network that maximizes correlative information transfer with domain constraints, demonstrating superior separation capability in numerical examples.
The brain effortlessly extracts latent causes of stimuli, but how it does this at the network level remains unknown. Most prior attempts at this problem proposed neural networks that implement independent component analysis which works under the limitation that latent causes are mutually independent. Here, we relax this limitation and propose a biologically plausible neural network that extracts correlated latent sources by exploiting information about their domains. To derive this network, we choose maximum correlative information transfer from inputs to outputs as the separation objective under the constraint that the outputs are restricted to their presumed sets. The online formulation of this optimization problem naturally leads to neural networks with local learning rules. Our framework incorporates infinitely many source domain choices and flexibly models complex latent structures. Choices of simplex or polytopic source domains result in networks with piecewise-linear activation functions. We provide numerical examples to demonstrate the superior correlated source separation capability for both synthetic and natural sources.