Improving Visualization, Scalability and Performance of Multiclass Problems with SVM Manifold Learning

Silva, Catarina; Bernardete Ribeiro

http://hdl.handle.net/10400.8/13037

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Improving visualization, scalability and performance of multiclass problems with SVM manifold learning.pdf	We propose a learning framework to address multiclass challenges, namely visualization, scalability and performance. We focus on supervised problems by presenting an approach that uses prior information about training labels, manifold learning and support vector machines (SVMs). We employ manifold learning as a feature reduction step, nonlinearly embedding data in a low dimensional space using Isomap (Isometric Mapping), enhancing geometric characteristics and preserving the geodesic distance within the manifold. Structured SVMs are used in a multiclass setting with benefits for final multiclass classification in this reduced space. Results on a text classification toy example and on ISOLET, an isolated letter speech recognition problem, demonstrate the remarkable visualization capabilities of the method for multiclass problems in the severely reduced space, whilst improving SVMs baseline performance.	329.42 KB	Adobe PDF	Download

Send Feedback

Authors

Silva, Catarina

Bernardete Ribeiro

Abstract(s)

We propose a learning framework to address multiclass challenges, namely visualization, scalability and performance. We focus on supervised problems by presenting an approach that uses prior information about training labels, manifold learning and support vector machines (SVMs). We employ manifold learning as a feature reduction step, nonlinearly embedding data in a low dimensional space using Isomap (Isometric Mapping), enhancing geometric characteristics and preserving the geodesic distance within the manifold. Structured SVMs are used in a multiclass setting with benefits for final multiclass classification in this reduced space. Results on a text classification toy example and on ISOLET, an isolated letter speech recognition problem, demonstrate the remarkable visualization capabilities of the method for multiclass problems in the severely reduced space, whilst improving SVMs baseline performance.

Description

9th International Conference on Adaptive and Natural Computing Algorithms, ICANNGA 200923 April 2009 through 25 April 2009 - Code 83287

Keywords

Support Vector Machine Independent Component Analysis Geodesic Distance Generalize Regression Neural Network Nonlinear Dimensionality Reduction

URI

http://hdl.handle.net/10400.8/13037

Citation

Silva, C., Ribeiro, B. (2009). Improving Visualization, Scalability and Performance of Multiclass Problems with SVM Manifold Learning. In: Kolehmainen, M., Toivanen, P., Beliczynski, B. (eds) Adaptive and Natural Computing Algorithms. ICANNGA 2009. Lecture Notes in Computer Science, vol 5495. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04921-7_38.