Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks

• المؤلف الرئيسي: Wang, Lipo.
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2012
• الموضوعات: DRNTU::Engineering::Electrical and electronic engineering
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/94091; http://hdl.handle.net/10220/8195
• المؤسسة: Nanyang Technological University

In this paper, we show that noise injection into inputs in unsupervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the...