Associative memory and deep learning with Hebbian synaptic and structural plasticity

The brain achieves complex information processing and cognitive functions leveraging synaptic learning mechanisms that are local, asynchronous, online and Hebbian in nature. Our work here investigates a neural network model with localized Hebbian plasticity that can perform associative memory and multilayer representation learning. This functionality is achieved with a brain-like modular hybrid architecture combining feedforward and recurrent processing pathways. We evaluate the model on the MNIST and F-MNIST datasets and propose that several aspects of the model are attractive for machine learning and brain-like neuromorphic hardware design.