Deep transfer learning for classification of time-delayed Gaussian networks

Chaturvedi, Iti, Ong, Yew Soon, and Arumugam, Rajesh Vellore (2015) Deep transfer learning for classification of time-delayed Gaussian networks. Signal Processing, 110. pp. 250-262.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1016/j.sigpro.2014.09...
24


Abstract

In this paper, we propose deep transfer learning for classification 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 different 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 classification 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 offensive formations in the Basketball games can be derived from the deep network.

Item ID: 63357
Item Type: Article (Research - C1)
ISSN: 1872-7557
Keywords: Deep neural networks, Gaussian networks, Manifold, Time-delays, Transfer learning, Variable-order
Copyright Information: © 2014 Elsevier B.V. All rights reserved.
Funders: Agency for Science, Technology and Research, Singapore (A*STAR), Centre for Computational Intelligence (C2I)
Projects and Grants: A*STAR Grant No. 1121720013
Date Deposited: 11 Aug 2020 22:14
FoR Codes: 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation @ 70%
11 MEDICAL AND HEALTH SCIENCES > 1106 Human Movement and Sports Science > 110699 Human Movement and Sports Science not elsewhere classified @ 30%
SEO Codes: 97 EXPANDING KNOWLEDGE > 970117 Expanding Knowledge in Psychology and Cognitive Sciences @ 100%
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page