Learning Efficient Backprojections Across Cortical Hierarchies in Real Time

Abstract

Models of sensory processing and learning in physical substrates (such as the cortex) need to efficiently assign credit to synapses in all areas. In deep learning, a well-established solution is error backpropagation; this however carries several biologically implausible requirements, such as weight transport from feed-forward to feedback paths. We present Phaseless Alignment Learning (PAL), a biologically plausible approach for learning efficient feedback weights in layered cortical hierarchies. Our dynamical system enables the simultaneous learning of all weights with always-on plasticity, and exclusively utilizes information locally available at the synapses. PAL is entirely phase-free, avoiding the need for forward and backward passes or phased learning, and enables efficient error propagation across multi-layer cortical hierarchies, while maintaining bio-physically plausible signal transport and learning.