An analysis of inhibitory pseudo-interconnections in unsupervised neural networks

Minh-Triet Tran; Nam Do-Hoang Le

doi:10.1117/12.2052652

24 December 2013 An analysis of inhibitory pseudo-interconnections in unsupervised neural networks

Minh-Triet Tran, Nam Do-Hoang Le

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.

Citation Download Citation

Minh-Triet Tran and 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); https://doi.org/10.1117/12.2052652

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available