DMCA
Controlling the Sensitivity of Support Vector Machines (1999)
Venue: | Proceedings of the International Joint Conference on AI |
Citations: | 106 - 4 self |
Citations
13212 | Statistical Learning Theory
- Vapnik
- 1998
(Show Context)
Citation Context ...erformance using receiver operating characteristic (ROC) curves. We then illustrate their use on real-life medical diagnostic tasks. 1 Introduction. Since their introduction by Vapnik and coworkers [ =-=Vapnik, 1995-=-; Cortes and Vapnik, 1995 ] , Support Vector Machines (SVMs) have been successfully applied to a number of real world problems such as handwritten character and digit recognition [ Scholkopf, 1997; C... |
3701 | Support-vector networks - Cortes, Vapnik - 1995 |
3468 | UCI Repository of machine learning databases - Blake, Merz |
726 | Training Support Vector Machine: An application to Face Detection - Osuna, Freund, et al. |
196 | Evaluation of Diagnostic Systems: Methods from Signal Detection Theory. - SWETS, PICKETT - 1982 |
152 | Support vector learning. - Scholkopf - 1997 |
114 | Comparison of learning algorithms for handwritten digit recognition.
- LeCun
- 1995
(Show Context)
Citation Context ...Vapnik, 1995 ] , Support Vector Machines (SVMs) have been successfully applied to a number of real world problems such as handwritten character and digit recognition [ Scholkopf, 1997; Cortes, 1995; =-=LeCun et al., 1995-=-; Vapnik, 1995 ] , face detection [ Osuna et al., 1997 ] and speaker identication [ Schmidt, 1996 ] . They exhibit a remarkable resistance to overtting, a feature explained by the fact that they dir... |
36 | Optimizing Classifiers for Imbalanced Training Sets - Karakoulas, Shawe-Taylor - 1999 |
35 | Further results on the margin distribution
- Shawe-Taylor, Cristianini
- 1999
(Show Context)
Citation Context ...C P k i + hw;wi subject to y i (hw;x i i+ b) 1 i , with i 0 (3) with k = 1 and k = 2. A theoretical analysis of both algorithms has recently been provided by Shawe-Taylor and Cristianini [ =-=Shawe-Taylor and Cristianini, 1999-=- ] , based on the concept of \margin distributions". For many decision support systems it is important to distinguish the two types of errors that can arise: a false alarm is usually not as expensive ... |
33 | Identifying speaker with support vector networks
- Schmidt
- 1996
(Show Context)
Citation Context ...d problems such as handwritten character and digit recognition [ Scholkopf, 1997; Cortes, 1995; LeCun et al., 1995; Vapnik, 1995 ] , face detection [ Osuna et al., 1997 ] and speaker identication [ =-=Schmidt, 1996-=- ] . They exhibit a remarkable resistance to overtting, a feature explained by the fact that they directly implement the principle of Structural Risk Minimization [ Vapnik, 1995 ] . For noise-free cl... |
30 | The Kernel-Adatron: A fast and simple learning procedure for Support Vector Machines - Friess, Cristianini, et al. - 1998 |
23 |
Signal detectability: the use of ROC curves and their analyses.
- Centor
- 1991
(Show Context)
Citation Context ...of correctly classied individuals without the disease. ROC analysis is a classical method in Signal Detection Theory [ Swets and Pickett, 1982 ] , and is used also in statistics, medical diagnosis [ =-=Centor, 1991-=- ] and more recently in Machine Learning as an alternative method for comparing learning systems [ Provost et al., 1998 ] . ROC space denotes a coordinate system used for visualizing the performance o... |
13 | Automated identification of tubercle bacilli in sputum. A preliminary investigation. - Veropoulos, Learmonth, et al. - 1999 |
5 |
Optimizing classi for imbalanced training sets
- Karakoulas, Shawe-Taylor
- 1999
(Show Context)
Citation Context ... related technique to the one proposed in this paper. Studying the case of very imbalanced datasets (where points of one class are much more numerous than points of the other class), the authors of [ =-=Karakoulas and Shawe-Taylor, 1999-=- ] proposed an algorithm where the labels are changed in such a way as to obtain a larger margin on the side of the smaller class. 2.1. We can readily generalise the soft margin approach (3): w x i ... |
4 | The automatic identification of tubercle bacilli using image processing and neural computing techniques - Veropoulos, Campbell, et al. - 1998 |
2 |
Prediction of Generalisation Ability in Learning Machines
- Cortes
- 1995
(Show Context)
Citation Context ...5; Cortes and Vapnik, 1995 ] , Support Vector Machines (SVMs) have been successfully applied to a number of real world problems such as handwritten character and digit recognition [ Scholkopf, 1997; =-=Cortes, 1995-=-; LeCun et al., 1995; Vapnik, 1995 ] , face detection [ Osuna et al., 1997 ] and speaker identication [ Schmidt, 1996 ] . They exhibit a remarkable resistance to overtting, a feature explained by th... |
2 | Fact sheet no 104: Tuberculosis - WHO - 1998 |
1 |
The case against accuracy estimation for comapring induction algorithms
- Provost, Fawcett, et al.
- 1998
(Show Context)
Citation Context ...Theory [ Swets and Pickett, 1982 ] , and is used also in statistics, medical diagnosis [ Centor, 1991 ] and more recently in Machine Learning as an alternative method for comparing learning systems [ =-=Provost et al., 1998-=- ] . ROC space denotes a coordinate system used for visualizing the performance of a classier, where the true positive rate is plotted on the y-axis, and the false positive rate on the x-axis. In thi... |
1 |
The automated identi of tubercle bacilli using image processing and recognition techniques
- Veropoulos, Campbell, et al.
- 1998
(Show Context)
Citation Context ... part of the latter curve could be plotted though this feature would depend on the training algorithm used [ Friess et al., 1998 ] . 4. TB dataset. This dataset derives from one of our own projects [ =-=Veropoulos et al., 1998-=-; 1999 ] . The task involves classication of image objects (TB bacilli or non-bacilli) on images captured using a microscope. It is intended as part of a system being developed for semi-automated dia... |
1 | The automated identi of tubercle bacilli in sputum: A preliminary investigation. Analytical and Quantitative Cytology and Histology, to appear - Veropoulos, Learmonth, et al. - 1999 |