Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Signal Processing
Implementation Of Large Neural Networks Using Decomposition, Henry Selvaraj, H. Niewiadomski, P. Buciak, M. Pleban, Piotr Sapiecha, Tadeusz Luba, Venkatesan Muthukumar
Implementation Of Large Neural Networks Using Decomposition, Henry Selvaraj, H. Niewiadomski, P. Buciak, M. Pleban, Piotr Sapiecha, Tadeusz Luba, Venkatesan Muthukumar
Electrical & Computer Engineering Faculty Research
The article presents methods of dealing with huge data in the domain of neural networks. The decomposition of neural networks is introduced and its efficiency is proved by the authors’ experiments. The examinations of the effectiveness of argument reduction in the above filed, are presented. Authors indicate, that decomposition is capable of reducing the size and the complexity of the learned data, and thus it makes the learning process faster or, while dealing with large data, possible. According to the authors experiments, in some cases, argument reduction, makes the learning process harder.
Wavelet Domain Communication System (Wdcs): Packet-Based Wavelet Spectral Estimation And M-Ary Signaling, Marion Jay F. Lee
Wavelet Domain Communication System (Wdcs): Packet-Based Wavelet Spectral Estimation And M-Ary Signaling, Marion Jay F. Lee
Theses and Dissertations
A recently proposed Wavelet Domain Communication System (WDCS) using transform domain processing demonstrated excellent interference avoidance capability under adverse environmental conditions. This work extends previous results by: 1) incorporating a wavelet packet decomposition technique, 2) demonstrating M-Ary signaling capability, and 3) providing increased adaptivity over a larger class of interference signals. The newly proposed packet-based WDCS is modeled and its performance characterized using MATLAB®. In addition, the WDCS response to two scenarios simulating Doppler effects and physical separation of transceivers are obtained. The fundamental metric for analysis and performance evaluation is bit error rate (Pb). Relative to …