Uniformly sparse neural networks

Siamack Haghighi

doi:10.1117/12.140147

1 July 1992 Uniformly sparse neural networks

Siamack Haghighi

Proceedings Volume 1710, Science of Artificial Neural Networks; (1992) https://doi.org/10.1117/12.140147
Event: Aerospace Sensing, 1992, Orlando, FL, United States

Abstract

Application of neural networks to problems with a large number of sensory inputs is severely limited when the processing elements (PEs) need to be fully connected. This paper presents a new network model in which a trade off between the number of connections to a node and the number of processing layers can be made. This trade off is an important issue in the VLSI implementation of neural networks. The performance and capability of a hierarchical pyramidal network architecture of limited fan-in PE layers is analyzed. Analysis of this architecture requires the development of a new learning rule, since each PE has access to limited information about the entire network input. A spatially local unsupervised training rule is developed in which each PE optimizes the fraction of its output variance contributed by input correlations, resulting in PEs behaving as adaptive local correlation detectors. It is also shown that the output of a PE optimally represents the mutual information among the inputs to that PE. Applications of the developed model in image compression and motion detection are presented.

Citation Download Citation

Siamack Haghighi "Uniformly sparse neural networks", Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); https://doi.org/10.1117/12.140147

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