Asymptotic learning in feedforward networks with binary symmetric channels

Zhang, Z, Chong, E, Pezeshki, A and Moran, W 2013, 'Asymptotic learning in feedforward networks with binary symmetric channels', in R. Ward and L. Deng (ed.) Proceedings of the 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), Vancouver, Canada, 26-31 May 2013, pp. 6610-6614.


Document type: Conference Paper
Collection: Conference Papers

Title Asymptotic learning in feedforward networks with binary symmetric channels
Author(s) Zhang, Z
Chong, E
Pezeshki, A
Moran, W
Year 2013
Conference name ICASSP 2013
Conference location Vancouver, Canada
Conference dates 26-31 May 2013
Proceedings title Proceedings of the 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013)
Editor(s) R. Ward and L. Deng
Publisher IEEE
Place of publication United States
Start page 6610
End page 6614
Total pages 5
Abstract Each of a large number of nodes takes a measurement in sequence to decide between two hypotheses about the state of the world. Each node also has available the decisions of some of its immediate predecessors and uses these and its own measurement to make its decision. Each node broadcasts its decision through a binary symmetric channel, which randomly flips the decision. The question treated here is whether there exists a decision strategy consisting of a sequence of likelihood ratio tests such that the decisions approach the true hypothesis as the number of nodes increases. We show that if each node learns from bounded number of predecessors, then the decisions cannot converge to the underlying truth. We show that if each node learns from all predecessors then the decisions converge in probability to the underlying truth when the flipping probabilities are bounded away from 1/2. We also derive, in the case when the flipping probabilities tend to 1/2, a condition on the convergence rate of the flipping probabilities that is required for the decisions to converge to the true hypothesis in probability.
Subjects Signal Processing
Approximation Theory and Asymptotic Methods
DOI - identifier 10.1109/ICASSP.2013.6638940
Copyright notice © 2013 IEEE
ISBN 9781479903566
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 1 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 86 Abstract Views  -  Detailed Statistics
Created: Tue, 29 Sep 2015, 10:26:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us