Thumbnail
Access Restriction
Open

Author Srivastava, Rupesh Kumar ♦ Masci, Jonathan ♦ Kazerounian, Sohrob ♦ Gomez, Faustino ♦ Schmidhuber, Jürgen
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Description Local competition among neighboring neurons is common in biological neu-ral networks (NNs). In this paper, 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. 1
In Advances In Neural Information Processing Systems, 2013
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article