Compete to Compute
Part of: Advances in Neural Information Processing Systems 26 (NIPS 2013)
[PDF] [BibTeX] [Reviews]Authors
Conference Event Type: Poster
Abstract
Local competition among neighboring neurons is common in biological neural networks (NNs). We apply the concept to gradient-based, backprop-trained artificial multilayer NNs. NNs with competing linear units tend to outperform those with non-competing nonlinear units, and avoid catastrophic forgetting when training sets change over time.