Ernst Haselsteiner, Jose C. Principe  Home/Search
Context
Related
| dpmi.tugraz.ac.at/~hasi...nc2000.ps.gz Cached: PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
PS.gz PS Image Update HelpFrom: dpmi.tugraz.ac.at/~hasi/pubs (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: This paper describes a new approach in supervised learning for classification problems. Usually each example is assigned a label, which represents the class information of the example. During training these labels are used as the desired outputs of the classifier and the classifier is tuned by minimizing some error criterion like MSE. As the chosen class labels are part of the error criterion they play an important role in the adaption process and therefore using suitable labels becomes very... (Update)
Similar documents based on text: More All
0.2: Target Prescreening based on a Quadratic Gamma.. - Principe.. (Correct)
0.2: Neural Based Methods for Time Series Classification - Haselsteiner (2000) (Correct)
0.2: Improving Learning by Using Dynamic Targets - Haselsteiner (Correct)
BibTeX entry: (Update)
@misc{ haselsteiner-supervised,
author = "Ernst Haselsteiner and Jose C. Principe",
title = "Supervised Learning without Numerical Targets - An Information Theoretic
Approach",
url = "citeseer.ist.psu.edu/haselsteiner00supervised.html" }
Citations (may not include all citations):1447 A mathematical theory of communication (context) - Shannon - 1948
897 Introduction to statistical pattern recognition (context) - Fukunaga - 1990
209 On estimation of a probability density function and mode - Parzen - 1962
169 Information theory and statistical mechanics (context) - Jaynes - 1957
108 Theory of probability (context) - Jeffreys - 1939
73 Serial order: A parallel distributed processing approach (context) - Jordan - 1986
15 moving targets (context) - Rohwer - 1990
8 Complete gradient optimization of a recurrent network applie.. (context) - Watrous, Ladendorf et al. - 1990
7 Pose estimation in SAR using an information theoretic criter.. (context) - Principe, Xu - 1998
3 entropy and information potential for neural computation (context) - Xu - 1999
1 Dynamic targets - adapting supervised learning to time serie.. - Haselsteiner - 1999
1 chapter InformationTheoretic Learning (context) - Principe, Xu et al. - 2000
1 Some fundamental questions of information therory (context) - Renyi - 1976
Documents on the same site (http://www.dpmi.tu-graz.ac.at/~hasi/pubs.html): More
Improving Learning by Using Dynamic Targets - Haselsteiner (Correct)
Neural Based Methods for Time Series Classification - Haselsteiner (2000) (Correct)
Time Series Classification Using Adaptive Dynamic Targets - Haselsteiner (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC