2019/08/02 by Gabrielle K. Liu, Liu, Gabrielle K. · 1 voice
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE) #cs.LG #cs.NE #stat.ML
paper · pdf · doi:10.48550/arxiv.1908.01052
9 pages, 6 figures, 1 table
arxiv published 2019/08/02 · arxiv created 2019/08/17 · arxiv updated 2019/08/20
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.