Learning deep and wide: A spectral method for learning deep networks

Shao, Ling, Wu, Di and Li, Xuelong (2014) Learning deep and wide: A spectral method for learning deep networks. IEEE Transactions on Neural Networks and Learning Systems, 25 (12). pp. 2303-2308. ISSN 2162-237X

Full text not available from this repository.


Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving many computer vision-related tasks. We propose the multispectral neural networks (MSNN) to learn features from multicolumn deep neural networks and embed the penultimate hierarchical discriminative manifolds into a compact representation. The low-dimensional embedding explores the complementary property of different views wherein the distribution of each view is sufficiently smooth and hence achieves robustness, given few labeled training data. Our experiments show that spectrally embedding several deep neural networks can explore the optimum output from the multicolumn networks and consistently decrease the error rate compared with a single deep network.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Pure Connector
Date Deposited: 01 Feb 2017 02:18
Last Modified: 03 Jul 2023 09:30
URI: https://ueaeprints.uea.ac.uk/id/eprint/62269
DOI: 10.1109/TNNLS.2014.2308519

Actions (login required)

View Item View Item