![](/images/graphics-bg.png)
Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation
Joint Authors
De Meyer, K.
Kompass, R.
Spratling, M. W.
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2009, Issue 2009 (31 Dec. 2009), pp.1-19, 19 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2009-05-05
Country of Publication
Egypt
No. of Pages
19
Main Subjects
Abstract EN
This paper demonstrates that nonnegative matrix factorisation is mathematically related to a class of neural networks that employ negative feedback as a mechanism of competition.
This observation inspires a novel learning algorithm which we call Divisive Input Modulation (DIM).
The proposed algorithm provides a mathematically simple and computationally efficient method for the unsupervised learning of image components, even in conditions where these elementary features overlap considerably.
To test the proposed algorithm, a novel artificial task is introduced which is similar to the frequently-used bars problem but employs squares rather than bars to increase the degree of overlap between components.
Using this task, we investigate how the proposed method performs on the parsing of artificial images composed of overlapping features, given the correct representation of the individual components; and secondly, we investigate how well it can learn the elementary components from artificial training images.
We compare the performance of the proposed algorithm with its predecessors including variations on these algorithms that have produced state-of-the-art performance on the bars problem.
The proposed algorithm is more successful than its predecessors in dealing with overlap and occlusion in the artificial task that has been used to assess performance.
American Psychological Association (APA)
Spratling, M. W.& De Meyer, K.& Kompass, R.. 2009. Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation. Computational Intelligence and Neuroscience،Vol. 2009, no. 2009, pp.1-19.
https://search.emarefa.net/detail/BIM-467575
Modern Language Association (MLA)
Spratling, M. W.…[et al.]. Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation. Computational Intelligence and Neuroscience No. 2009 (2009), pp.1-19.
https://search.emarefa.net/detail/BIM-467575
American Medical Association (AMA)
Spratling, M. W.& De Meyer, K.& Kompass, R.. Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation. Computational Intelligence and Neuroscience. 2009. Vol. 2009, no. 2009, pp.1-19.
https://search.emarefa.net/detail/BIM-467575
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-467575