Results 1 - 10 of 30,411

Table 1: Test Error Rates on the USPS Handwritten Digit Database.

in Nonlinear Component Analysis as a Kernel Eigenvalue Problem
by Bernhard Schölkopf, Alexander Smola, Klaus-Robert Müller
"... In PAGE 12: ... It simply tries to separate the training data by a hyperplane with large margin. Table1 illustrates two advantages of using nonlinear kernels. First, per- formance of a linear classifier trained on nonlinear principal components is better than for the same number of linear components; second, the perfor- mance for nonlinear components can be further improved by using more components than is possible in the linear case.... ..."

Table 3. Average (across all classes) of sensitivity, speciflcity and the MCC for all predictors on the non-plant data. Sorting Results Non-plant Data Detection Network Sorter Kernel Sensitivity Speciflcity MCC Accuracy

in Detecting and Sorting Targeting Peptides with Neural Networks and
by Support Vector Machines, John Hawkins, Mikael Bodén
"... In PAGE 13: ...777 84.7% Note: See Table3 for details. and recurrent architectures.... ..."

Table 6: Results from support vector machine

in General Terms
by Adrian Schröter
"... In PAGE 6: ...java B.java Figure 4: Comparison of predicted and observed ranking In Table6 (d) we obtained a precision of 0.6671 for the test in version 2.... In PAGE 6: ... recall = correct predicted failures all failures As an example, the recall of the test in version 2.0 shown in Table6 (d) indicates that over two third of the failure-prone components are actually identified as failure-prone. Again, a random guess would have had a probability of 0.... In PAGE 6: ... For example, take the test in version 2.0 of Table6 (b) with a recall of about 0.... In PAGE 6: ...iles. For example, take the test in version 2.0 of Table 6(b) with a recall of about 0.1 and Table6 (d) with a recall of about 0.7.... In PAGE 8: ...g., in Table6 (d), the precision for the top 5% of version 2.1 is substantially higher than the overall precision (90% vs.... In PAGE 8: ...esults from version 2.0 and 2.1 are similar with respect to classifi- cation. Take for example Table6 (d), the recall and precision obtained from testing in version 2.... ..."

Table 2: Parameter values of proposed kernels and Support Vector Machines

in Convolution kernels with feature selection for natural language processing tasks
by Jun Suzuki, Hideki Isozaki, Eisaku Maeda 2004
"... In PAGE 6: ... Support Vector Machine (SVM) was selected as the kernel-based classifier for training and classifi- cation. Table2 shows some of the parameter values that we used in the comparison. We set thresholds of = 2:7055 (FSSK1) and = 3:8415 (FSSK2) for the proposed methods; these values represent the 10% and 5% level of significance in the 2 distribu- tion with one degree of freedom, which used the 2 significant test.... ..."
Cited by 4

TABLE I IN PUTS TO THE NEURAL NETWORK AND SUPPORT VECTOR MACHINE MODELS

in Energy Constrained Generation Dispatch based on Price Forecasts Including Expected Values
by Risk, Damien C. Sansom, Student Member, Tapan K Saha, Senior Member

Table 2: Results on the Toxicology Dataset Support Vector Machines

in Automated approaches for classifying structures
by Mukund Deshpande, Michihiro Kuramochi, George Karypis
"... In PAGE 9: ... Varying the Misclassification Cost The first set of experiments were conducted by changing the misclassifi- cation cost in the SVM classifier so as to associate higher misclassification cost for incorrectly classifying positive examples. The results of the experiments using SVM and classification rules classifier are displayed in Table2 . Each cell in the table indicates the area under the ROC curve for that classifier and misclassification cost value.... ..."

Table 5: Results on the DTP-AIDS Dataset Support Vector Machines

in Automated approaches for classifying structures
by Mukund Deshpande, Michihiro Kuramochi, George Karypis
"... In PAGE 11: ... 4.2 Evaluation on the DTP-AIDS Dataset Table5 displays the results of our two classifier on the DTP-AIDS dataset. Since the class distribution for the two clas- sification problems on the AIDS dataset is quite different we have experimented with different sets of misclassification... ..."

Table 2: Results on the Toxicology Dataset Support Vector Machines

in Automated Approaches for Classifying Structures
by Mukund Deshpande, Michihiro Kuramochi, George Karypis
"... In PAGE 9: ... Varying the Misclassification Cost The first set of experiments were conducted by changing the misclassifi- cation cost in the SVM classifier so as to associate higher misclassification cost for incorrectly classifying positive examples. The results of the experiments using SVM and classification rules classifier are displayed in Table2 . Each cell in the table indicates the area under the ROC curve for that classifier and misclassification cost value.... ..."

Table 5: Results on the DTP-AIDS Dataset Support Vector Machines

in Automated Approaches for Classifying Structures
by Mukund Deshpande, Michihiro Kuramochi, George Karypis
"... In PAGE 11: ... 4.2 Evaluation on the DTP-AIDS Dataset Table5 displays the results of our two classifier on the DTP-AIDS dataset. Since the class distribution for the two clas- sification problems on the AIDS dataset is quite different we have experimented with different sets of misclassification... ..."

Table 2: Results on the Toxicology Dataset Support Vector Machines

in Automated approaches for classifying structures
by Mukund Deshpande, Michihiro Kuramochi, George Karypis
"... In PAGE 9: ... Varying the Misclassification Cost The first set of experiments were conducted by changing the misclassifi- cation cost in the SVM classifier so as to associate higher misclassification cost for incorrectly classifying positive examples. The results of the experiments using SVM and classification rules classifier are displayed in Table2 . Each cell in the table indicates the area under the ROC curve for that classifier and misclassification cost value.... ..."
Results 1 - 10 of 30,411