DeepAI AI Chat
Log In Sign Up

Behavioral Experiments for Understanding Catastrophic Forgetting

by   Samuel J. Bell, et al.

In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too. We apply the techniques of experimental psychology to investigating catastrophic forgetting in neural networks. We present a series of controlled experiments with two-layer ReLU networks, and exploratory results revealing a new understanding of the behavior of catastrophic forgetting. Alongside our empirical findings, we demonstrate an alternative, behavior-first approach to investigating neural network phenomena.


page 1

page 2

page 3

page 4


Catastrophic Importance of Catastrophic Forgetting

This paper describes some of the possibilities of artificial neural netw...

Overcoming Catastrophic Forgetting by XAI

Explaining the behaviors of deep neural networks, usually considered as ...

Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization

Interpreting the behaviors of Deep Neural Networks (usually considered a...

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics

A central challenge in developing versatile machine learning systems is ...

Empirical investigations on WVA structural issues

In this paper we want to present the results of empirical verification o...

A comprehensive, application-oriented study of catastrophic forgetting in DNNs

We present a large-scale empirical study of catastrophic forgetting (CF)...

On the role of neurogenesis in overcoming catastrophic forgetting

Lifelong learning capabilities are crucial for artificial autonomous age...