Weight Friction: A Simple Method to Overcome Catastrophic Forgetting and Enable Continual Learning
This addresses the problem of catastrophic forgetting for researchers and practitioners in machine learning, offering an incremental improvement over existing continual learning techniques.
The paper tackles catastrophic forgetting in deep neural networks by proposing weight friction, a simple method that modifies gradient descent to enable continual learning, achieving comparable performance to current methods with improved computation and memory efficiency.
In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously learned tasks, a shortcoming known as catastrophic forgetting. In this research, we propose a simple method to overcome catastrophic forgetting and enable continual learning in neural networks. We draw inspiration from principles in neurology and physics to develop the concept of weight friction. Weight friction operates by a modification to the update rule in the gradient descent optimization method. It converges at a rate comparable to that of the stochastic gradient descent algorithm and can operate over multiple task domains. It performs comparably to current methods while offering improvements in computation and memory efficiency.