Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/82815
Title: Deep transfer learning for classification of time-delayed Gaussian networks
Authors: Chaturvedi, Iti
Ong, Yew Soon
Arumugam, R. V.
Keywords: Gaussian networks
Deep Neural Networks
Transfer Learning
Manifold
Time-delays
Variable-order
Issue Date: 2014
Source: Chaturvedi, I., Ong, Y. S., & Arumugam, R. V. (2015). Deep transfer learning for classification of time-delayed Gaussian networks. Signal Processing, 110, 250-262.
Series/Report no.: Signal Processing
Abstract: In this paper, we propose deep transfer learning for classifcation of Gaussian networks with time-delayed regulations. To ensure robust signaling, most real world problems from related domains have inherent alternate pathways that can be learned incrementally from a stable form of the baseline. In this paper, we leverage on this characteristic to address the challenges of complexity and scalability. The key idea is to learn high dimensional network motifs from low dimensional forms through a process of transfer learning. In contrast to previous work, we facilitate positive transfer by introducing a triangular inequality constraint, which provides a measure for the feasibility of mapping between di erent motif manifolds. Network motifs from different classes of Gaussian networks are used collectively to pre-train a deep neural network governed by a Lyapunov stability condition. The proposed framework is validated on time series data sampled from synthetic Gaussian networks and applied to a real world dataset for the classi cation of basketball games based on skill level. We observe an improvement in the range of [15-25]% in accuracy and a saving in the range of [25-600]% in computational cost on synthetic as well as realistic networks with time-delays when compared to existing state-of-the-art approaches. In addition, new insights into meaningful o ensive formations in the Basketball games can be derived from the deep network.
URI: https://hdl.handle.net/10356/82815
http://hdl.handle.net/10220/40335
ISSN: 0165-1684
DOI: 10.1016/j.sigpro.2014.09.009
Schools: School of Computer Engineering 
Rights: © 2014 Elsevier. This is the author created version of a work that has been peer reviewed and accepted for publication by Signal Processing, Elsevier. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1016/j.sigpro.2014.09.009].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Deep Transfer Learning for Classification of Time-Delayed Gaussian Networks.pdf632.35 kBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 10

34
Updated on May 8, 2024

Web of ScienceTM
Citations 10

29
Updated on Oct 28, 2023

Page view(s) 20

683
Updated on May 15, 2024

Download(s) 5

565
Updated on May 15, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.