Attention-Based Structural-Plasticity

Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-03
Main Authors: Kolouri, Soheil, Ketz, Nicholas, Zou, Xinyun, Krichmar, Jeffrey, Pilly, Praveen
Format: Article
Language:English
Subjects:
Algorithms
Back propagation
Brain
Lifelong learning
Machine learning
Neural networks
Plastic properties
Synapses
Test procedures
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several efforts towards overcoming catastrophic forgetting in neural networks. Here, we propose a biologically inspired method toward overcoming catastrophic forgetting. Specifically, we define an attention-based selective plasticity of synapses based on the cholinergic neuromodulatory system in the brain. We define synaptic importance parameters in addition to synaptic weights and then use Hebbian learning in parallel with backpropagation algorithm to learn synaptic importances in an online and seamless manner. We test our proposed method on benchmark tasks including the Permuted MNIST and the Split MNIST problems and show competitive performance compared to the state-of-the-art methods.
ISSN:2331-8422