Results 1 - 10 of 323,753

Table 2: For test function with two inputs, mean (over 50 data samples) and 95% confidence interval for standardized MSE at 225 test locations, and for the temperature and ozone datasets, cross-validated standardized MSE, for the six methods. Method Function with 2 inputs Temp. data Ozone data

in Nonstationary Covariance Functions for Gaussian Process Regression
by Christopher J. Paciorek, Mark J. Schervish 2004
Cited by 4

Table 2: For test function with two inputs, mean (over 50 data samples) and 95% confidence interval for standardized MSE at 225 test locations, and for the temperature and ozone datasets, cross-validated standardized MSE, for the six methods. Method Function with 2 inputs Temp. data Ozone data

in Nonstationary covariance functions for gaussian process regression
by Christopher J. Paciorek, Mark J. Schervish 2004
Cited by 4

Table 2: For test function with two inputs, mean (over 50 data samples) and 95% confidence interval for standardized MSE at 225 test locations, and for the temperature and ozone datasets, cross-validated standardized MSE, for the six methods. Method Function with 2 inputs Temp. data Ozone data

in Nonstationary Covariance Functions for Gaussian Process Regression
by Christopher J. Paciorek, Mark J. Schervish 2004
Cited by 4

Table 3. A comparison between the diagnosis of the circuit in Figure 5 done with Dague apos;s Expert System and with Neural Network with Sampling.

in A Neural Network Diagnosis Approach for Analog Circuits
by Alessandra Fanni, Alessandro Giua, MICHELE MARCHESI, AUGUSTO Montisci
"... In PAGE 17: ... As remarked before, however, it is a viable solu- tion only because we have a small number of test points (two in this example) and the circuit has a short transient. Comparison with Dague apos;s Expert System In Table3 we compare the results obtained us- ing our diagnostic system with sampling feature extraction (Neural Network with Sampling) with the results obtained by Dague apos;s expert system. Note that although only 12 faults are considered by Dague, our diagnostic system has been trained... ..."

Table 6: Neural network based sampling results for the Bayesian IV regression

in reduced rank models
by Lennart F. Hoogerheide, Johan F. Kaashoek, Herman K. Van Dijk 2004

Table 2: Diagnosis Results after Fault Filtering

in unknown title
by unknown authors 1999
"... In PAGE 7: ... While the number of candidate faults may be too large to be used directly for physical fault localization for some faults, the fault list size can be reduced sig- nificantly by removing node pairs that are not adja- cent in the layout or by performing accurate bridge fault simulation for candidate faults in a postprocess- ing step. Table2 presents the improvement made by filtering out node pairs that are not adjacent in the layout. A bridge fault extractor, FAULTAN [19], was used to perform bridge fault extraction from cell-based layout designs of the benchmark circuits.... ..."
Cited by 2

Table 2. Experimental Results for Fault Diagnosis of Multiple Point Faults

in Adaptive Techniques for Improving Delay Fault Diagnosis
by unknown authors
"... In PAGE 5: ... As can be seen, the number of suspects can be greatly reduced providing a much better diagnostic resolution. Table2 shows results for the case where multiple faults were injected in the circuit-under- test. In this case also, the number of suspects can be significantly reduced using the adaptive method.... ..."

Table 1 . Experimental Results for Fault Diagnosis of Single Point Faults

in Adaptive Techniques for Improving Delay Fault Diagnosis
by Jayabrata Ghosh-Dastidar, Nur A. Touba 1999
"... In PAGE 5: ...Experiments using the adaptive techniques described in this paper were performed for some of the ISCAS 85 benchmark circuits [Brglez 85]. Table1 shows results for the case where a single fault was injected in the circuit- under-test. The number of suspects obtained using the critical path tracing method described in [Girard 92] is shown.... ..."
Cited by 2

Table 2. Performance comparison of different neural network based classifiers.

in unknown title
by unknown authors 2002
"... In PAGE 7: ... Another reported measure, the accuracy, is the ratio between the total numbers of correctly classified instances to all the instances that exist in the test set. Table2 summarises the results obtained on the test set where the best classifiers, including 30 hidden units for SCG and 10 for BP learning method, have been chosen on the basis of validation error. These results are just a selection out of a number of configurations used for training the classifiers.... ..."
Cited by 2

TABLE 1 - Neural network diagnosis success rates

in Diagnosis Using Fault Trees Induced from Simulated Incipient Fault Case Data
by Paul J Nolan, Michael G Madden, Peter Muldoon
Results 1 - 10 of 323,753