Associative Memory and Deep Learning with 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.
Cite
Text
Ravichandran et al. "Associative Memory and Deep Learning with Hebbian Synaptic and Structural Plasticity." ICML 2023 Workshops: LLW, 2023.Markdown
[Ravichandran et al. "Associative Memory and Deep Learning with Hebbian Synaptic and Structural Plasticity." ICML 2023 Workshops: LLW, 2023.](https://mlanthology.org/icmlw/2023/ravichandran2023icmlw-associative/)BibTeX
@inproceedings{ravichandran2023icmlw-associative,
title = {{Associative Memory and Deep Learning with Hebbian Synaptic and Structural Plasticity}},
author = {Ravichandran, Naresh and Lansner, Anders and Herman, Pawel},
booktitle = {ICML 2023 Workshops: LLW},
year = {2023},
url = {https://mlanthology.org/icmlw/2023/ravichandran2023icmlw-associative/}
}