20 April 2015 Gaussian weighted neighborhood connectivity of nonlinear line attractor for learning complex manifolds
Author Affiliations +
The human brain has the capability to process high quantities of data quickly for detection and recognition tasks. These tasks are made simpler by the understanding of data, which intentionally removes redundancies found in higher dimensional data and maps the data onto a lower dimensional space. The brain then encodes manifolds created in these spaces, which reveal a specific state of the system. We propose to use a recurrent neural network, the nonlinear line attractor (NLA) network, for the encoding of these manifolds as specific states, which will draw untrained data towards one of the specific states that the NLA network has encoded. We propose a Gaussian-weighted modular architecture for reducing the computational complexity of the conventional NLA network. The proposed architecture uses a neighborhood approach for establishing the interconnectivity of neurons to obtain the manifolds. The modified NLA network has been implemented and tested on the Electro-Optic Synthetic Vehicle Model Database created by the Air Force Research Laboratory (AFRL), which contains a vast array of high resolution imagery with several different lighting conditions and camera views. It is observed that the NLA network has the capability for representing high dimensional data for the recognition of the objects of interest through its new learning strategy. A nonlinear dimensionality reduction scheme based on singular value decomposition has found to be very effective in providing a low dimensional representation of the dataset. Application of the reduced dimensional space on the modified NLA algorithm would provide fast and more accurate recognition performance for real time applications.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Theus H. Aspiras, Theus H. Aspiras, Vijayan K. Asari, Vijayan K. Asari, Wesam Sakla, Wesam Sakla, } "Gaussian weighted neighborhood connectivity of nonlinear line attractor for learning complex manifolds", Proc. SPIE 9477, Optical Pattern Recognition XXVI, 94770E (20 April 2015); doi: 10.1117/12.2179889; https://doi.org/10.1117/12.2179889


A review on face recognition techniques
Proceedings of SPIE (January 27 2013)
Radial Basis Function network for handwritten digit recognition
Proceedings of SPIE (September 01 1993)
Bootstrapping color constancy
Proceedings of SPIE (May 18 1999)
Multisensor user authentication
Proceedings of SPIE (September 01 1993)

Back to Top