Associative memory and deep learning with Hebbian synaptic and structural plasticity
Keywords: brain-like, biologically plausible, unsupervised learning, Hebbian, synaptic plasticity, structural plasticity, modular network, cortex
TL;DR: Modelling associative memory and multilayer networks with biologically plausible modular architecture and Hebbian synaptic and structural plasticity
Abstract: 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.
Submission Number: 17
Loading