Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Localized Learning: Decentralized Model Updates via Non-Global Objectives

Associative memory and deep learning with Hebbian synaptic and structural plasticity

Naresh Balaji Ravichandran · Anders Lansner · Pawel Herman

Keywords: [ Unsupervised Learning ] [ cortex ] [ modular network ] [ Hebbian ] [ biologically plausible ] [ synaptic plasticity ] [ structural plasticity ] [ brain-like ]


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.

Chat is not available.