Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network
Bax I, Heidemann G, Ritter H (2005)
In: Proceedings of the 9th IAPR Conference on Machine Vision Applications., 9. Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo: 464-467.
Sammelwerksbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Bax, Ingo;
Heidemann, Gunther;
Ritter, HelgeUniBi ![](https://pub.uni-bielefeld.de/images/icon_orcid.png)
![](https://pub.uni-bielefeld.de/images/icon_orcid.png)
Einrichtung
Abstract / Bemerkung
In this contribution we utilize recent advances in feature coding strategies for a hierarchical Neocognitron-like neu- ral architecture, which can be used for invariant recogni- tion of natural visual stimuli like objects or faces. Several researchers have identied that sparseness is an important coding principle for learning receptive eld proles that resemble response properties of simple cells in visual cor- tex. However, an ongoing discussion is concerned with the question whether sparseness should be imposed on the la- tent variables ñ as implicitly done in ICA or Sparse Coding ñ or if it should rather be imposed directly on the feature matrix. Since answers to this question have so far not been unique and were rather qualitative in nature, this paper in- vestigates the two possibilities by applying a recently in- troduced algorithm for Non-negative Matrix Factorization with Sparseness Constraints (NMFSC) to feature learning in a hierarchical recognition network. For this network, we compare recognition performance on several difcult image datasets under varying sparseness settings
Erscheinungsjahr
2005
Buchtitel
Proceedings of the 9th IAPR Conference on Machine Vision Applications
Band
9
Seite(n)
464-467
ISBN
4-901122-04-5
Page URI
https://pub.uni-bielefeld.de/record/2714182
Zitieren
Bax I, Heidemann G, Ritter H. Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network. In: Proceedings of the 9th IAPR Conference on Machine Vision Applications. Vol 9. Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo; 2005: 464-467.
Bax, I., Heidemann, G., & Ritter, H. (2005). Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network. Proceedings of the 9th IAPR Conference on Machine Vision Applications, 9, 464-467
Bax, Ingo, Heidemann, Gunther, and Ritter, Helge. 2005. “Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network”. In Proceedings of the 9th IAPR Conference on Machine Vision Applications, 9:464-467. Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo.
Bax, I., Heidemann, G., and Ritter, H. (2005). “Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network” in Proceedings of the 9th IAPR Conference on Machine Vision Applications, vol. 9, (Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo), 464-467.
Bax, I., Heidemann, G., & Ritter, H., 2005. Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network. In Proceedings of the 9th IAPR Conference on Machine Vision Applications. no.9 Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo, pp. 464-467.
I. Bax, G. Heidemann, and H. Ritter, “Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network”, Proceedings of the 9th IAPR Conference on Machine Vision Applications, vol. 9, Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo, 2005, pp.464-467.
Bax, I., Heidemann, G., Ritter, H.: Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network. Proceedings of the 9th IAPR Conference on Machine Vision Applications. 9, p. 464-467. Institute of Industrial Science, University of Tokyo, Tsukuba Science City, Japan (2005).
Bax, Ingo, Heidemann, Gunther, and Ritter, Helge. “Using Non-negative Sparse Profiles in a Hierarchical Feature Extraction Network”. Proceedings of the 9th IAPR Conference on Machine Vision Applications. Tsukuba Science City, Japan: Institute of Industrial Science, University of Tokyo, 2005.Vol. 9. 464-467.