Reducing catastrophic forgetting when evolving neural networks

04/05/2019
by   Joseph Early, et al.
0

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods are very prone to catastrophic forgetting (CF) - the act of overwriting previous knowledge about a task when learning a new task. Recent efforts have developed techniques for overcoming CF in learning systems, but no attempt has been made to apply these new techniques to evolutionary systems. This research presents a novel technique, weight protection, for reducing CF in evolutionary systems by adapting a method from learning systems. It is used in conjunction with other evolutionary approaches for overcoming CF and is shown to be effective at alleviating CF when applied to a suite of reinforcement learning tasks. It is speculated that this work could indicate the potential for a wider application of existing learning-based approaches to evolutionary systems and that evolutionary techniques may be competitive with or better than learning systems when it comes to reducing CF.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/25/2022

An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems

Multitask learning assumes that models capable of learning from multiple...
research
02/04/2020

Neuro-evolutionary Frameworks for Generalized Learning Agents

The recent successes of deep learning and deep reinforcement learning ha...
research
02/15/2021

Does Standard Backpropagation Forget Less Catastrophically Than Adam?

Catastrophic forgetting remains a severe hindrance to the broad applicat...
research
01/04/2018

Overcoming catastrophic forgetting with hard attention to the task

Catastrophic forgetting occurs when a neural network loses the informati...
research
01/18/2023

A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems

Despite the advancement of machine learning techniques in recent years, ...
research
10/15/2019

Embodiment dictates learnability in neural controllers

Catastrophic forgetting continues to severely restrict the learnability ...
research
06/16/2018

DynMat, a network that can learn after learning

To survive in the dynamically-evolving world, we accumulate knowledge an...

Please sign up or login with your details

Forgot password? Click here to reset