Výsledky vyhledávání - "Mahesh V. Joshi"

On evaluating performance of classifiers for rare classes

Autor: Mahesh V. Joshi

Publikováno v: ICDM

Predicting rare classes effectively is an important problem. The definition of effective classifier, embodied in the classifier evaluation metric, is however very subjective, dependent on the application domain. In this paper a wide variety of point-

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f782efe26e1a5947d5f349d02516653d
https://doi.org/10.1109/icdm.2002.1184018

Zobrazit plný text záznamu

Topic Learning from Few Examples

Autor: Huaiyu Zhu, Mahesh V. Joshi, Shivakumar Vaithyanathan

Publikováno v: Knowledge Discovery in Databases: PKDD 2003 ISBN: 9783540200857
PKDD

This paper describes a semi-supervised algorithm for single class learning with very few examples. The problem is formulated as a hierarchical latent variable model which is clipped to ignore classes not of interest. The model is trained using a mult

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::41253a2f85c1a9bc6d7f11aa8fd19dd1
https://doi.org/10.1007/978-3-540-39804-2_43

Zobrazit plný text záznamu

High Performance Data Mining

Autor: Vipin Kumar, Mahesh V. Joshi, Eui-Hong Han, Pang-Ning Tan, Michael Steinbach

Publikováno v: Lecture Notes in Computer Science ISBN: 9783540008521
VECPAR

Recent times have seen an explosive growth in the availability of various kinds of data. It has resulted in an unprecedented opportunity to develop automated data-driven techniques of extracting useful knowledge. Data mining, an important step in thi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5c444a675bbf4e692b8c3b9045b67054
https://doi.org/10.1007/3-540-36569-9_8

Zobrazit plný text záznamu

Evaluating boosting algorithms to classify rare classes: comparison and improvements

Autor: Mahesh V. Joshi, R.C. Agarwal, Vipin Kumar

Publikováno v: ICDM

Classification of rare events has many important data mining applications. Boosting is a promising meta-technique that improves the classification performance of any weak classifier. So far, no systematic study has been conducted to evaluate how boos

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::136f1aedc21c714f255128dd2b0fe196
https://doi.org/10.1109/icdm.2001.989527

Zobrazit plný text záznamu

Predicting Rare Classes: Comparing Two-Phase Rule Induction to Cost-Sensitive Boosting

Autor: Mahesh V. Joshi, Vipin Kumar, Ramesh C. Agarwal

Publikováno v: Principles of Data Mining and Knowledge Discovery ISBN: 9783540440376
PKDD

Learning good classifier models of rare events is a challenging task. On such problems, the recently proposed two-phase rule induction algorithm, PNrule, outperforms other non-meta methods of rule induction. Boosting is a strong meta-classifier appro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6ef4858f81e591093a8a1160ca5f02d7
https://doi.org/10.1007/3-540-45681-3_20

Zobrazit plný text záznamu

PNrule: A New Framework for Learning Classifier Models in Data Mining (A Case-Study in Network Intrusion Detection)

Autor: Ramesh Agarwal, Mahesh V. Joshi

Publikováno v: Proceedings of the 2001 SIAM International Conference on Data Mining.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7be584068a33faa3c6b2aee7553d342b
https://doi.org/10.1137/1.9781611972719.29

Zobrazit plný text záznamu

A high performance matrix multiplication algorithm for MPPs

Autor: Ramesh C. Agarwal, Susanne M. Balle, Prasad Palkar, Mahesh V. Joshi, Fred G. Gustavson

Publikováno v: Lecture Notes in Computer Science ISBN: 9783540609025

A 3-dimensional (3-D) matrix multiplication algorithm for massively parallel processing systems is presented. Performing the product of two matrices C=β C+α A B is viewed as solving a 2-dimensional problem in the 3-dimensional computational space.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1f6c1e4fa8476bb72a94ba500f55836b
https://doi.org/10.1007/3-540-60902-4_1

Zobrazit plný text záznamu

Conference

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Vyhledávací nástroje:

Upřesnit hledání