A Neural Network Model of Continual Learning with Cognitive Control

02/09/2022
by   Jacob Russin, et al.
0

Neural networks struggle in continual learning settings from catastrophic forgetting: when trials are blocked, new learning can overwrite the learning from previous blocks. Humans learn effectively in these settings, in some cases even showing an advantage of blocking, suggesting the brain contains mechanisms to overcome this problem. Here, we build on previous work and show that neural networks equipped with a mechanism for cognitive control do not exhibit catastrophic forgetting when trials are blocked. We further show an advantage of blocking over interleaving when there is a bias for active maintenance in the control signal, implying a tradeoff between maintenance and the strength of control. Analyses of map-like representations learned by the networks provided additional insights into these mechanisms. Our work highlights the potential of cognitive control to aid continual learning in neural networks, and offers an explanation for the advantage of blocking that has been observed in humans.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/11/2022

Continual Learning by Modeling Intra-Class Variation

It has been observed that neural networks perform poorly when the data o...
research
11/06/2018

Towards continual learning in medical imaging

This work investigates continual learning of two segmentation tasks in b...
research
04/24/2020

Dropout as an Implicit Gating Mechanism For Continual Learning

In recent years, neural networks have demonstrated an outstanding abilit...
research
03/07/2021

Embodied Continual Learning Across Developmental Time Via Developmental Braitenberg Vehicles

There is much to learn through synthesis of Developmental Biology, Cogni...
research
05/03/2020

Explaining How Deep Neural Networks Forget by Deep Visualization

Explaining the behaviors of deep neural networks, usually considered as ...
research
09/16/2020

Measuring Information Transfer in Neural Networks

Estimation of the information content in a neural network model can be p...
research
12/28/2022

Sparse Coding in a Dual Memory System for Lifelong Learning

Efficient continual learning in humans is enabled by a rich set of neuro...

Please sign up or login with your details

Forgot password? Click here to reset