24 December 2013 An analysis of inhibitory pseudo-interconnections in unsupervised neural networks
Author Affiliations +
Proceedings Volume 9067, Sixth International Conference on Machine Vision (ICMV 2013); 90671R (2013) https://doi.org/10.1117/12.2052652
Event: Sixth International Conference on Machine Vision (ICMV 13), 2013, London, United Kingdom
Abstract
Lateral connection is a fundamental element of human neural networks which enables sparse learning and topographical order in feature maps. Due to high complexity and computational cost, computer scientists tend to simplify it in practical implementations. To utilize the simplicity of traditional networks while preserving the effects of interconnections, the authors employ numerical filters in unsupervised learning networks. These filters suppress low activations and decorrelate high ones, which are similar to how inhibitory lateral connections behave. Inhibitory networks outperform conventional approach in both standard datasets CIFAR-10 and STL-10. Our method also yields competitive results in comparison with other single-layer unsupervised networks. Furthermore, it is promising to apply inhibitory networks into deep learning systems for complex recognition problem.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Minh-Triet Tran, Nam Do-Hoang Le, "An analysis of inhibitory pseudo-interconnections in unsupervised neural networks ", Proc. SPIE 9067, Sixth International Conference on Machine Vision (ICMV 2013), 90671R (24 December 2013); doi: 10.1117/12.2052652; https://doi.org/10.1117/12.2052652
PROCEEDINGS
5 PAGES


SHARE
Back to Top