Reducing Catastrophic Forgetting in Modular Neural Networks by Dynamic Information Balancing

by   Mohammed Amer, et al.
The University of Nottingham Malaysia Campus

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial intelligent systems. However, neural networks suffer from catastrophic forgetting when stressed with the challenge of continual learning. We investigate how to exploit modular topology in neural networks in order to dynamically balance the information load between different modules by routing inputs based on the information content in each module so that information interference is minimized. Our dynamic information balancing (DIB) technique adapts a reinforcement learning technique to guide the routing of different inputs based on a reward signal derived from a measure of the information load in each module. Our empirical results show that DIB combined with elastic weight consolidation (EWC) regularization outperforms models with similar capacity and EWC regularization across different task formulations and datasets.


page 1

page 2

page 3

page 4


Modular-Relatedness for Continual Learning

In this paper, we propose a continual learning (CL) technique that is be...

Dynamically Modular and Sparse General Continual Learning

Real-world applications often require learning continuously from a strea...

Routing Networks with Co-training for Continual Learning

The core challenge with continual learning is catastrophic forgetting, t...

Dissecting Catastrophic Forgetting in Continual Learning by Deep Visualization

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

Diffusion-based neuromodulation can eliminate catastrophic forgetting in simple neural networks

A long-term goal of AI is to produce agents that can learn a diversity o...

Measuring Information Transfer in Neural Networks

Estimation of the information content in a neural network model can be p...

Monitoring nonstationary processes based on recursive cointegration analysis and elastic weight consolidation

This paper considers the problem of nonstationary process monitoring und...

Please sign up or login with your details

Forgot password? Click here to reset