Results 1 - 10 of 72,829

Table 1. Quantified accuracy of the extended graph-shifts algorithm on two pathologies

in W.: Detection and Segmentation of Pathological Structures by the Extended Graph-Shifts Algorithm
by Jason J. Corso, Alan Yuille, Nancy L. Sicotte, Arthur Toga, Jason J. Corso, Alan Yuille, Nancy L. Sicotte, Arthur Toga
"... In PAGE 9: ... Again, the dataset was split in half for training and testing. Table1 (b) gives the detection rate Fig.... ..."
Cited by 1

Table 1. Quantified accuracy of the extended graph-shifts algorithm on two pathologies.

in W.: Detection and Segmentation of Pathological Structures by the Extended Graph-Shifts Algorithm
by Jason J. Corso, Alan Yuille, Nancy L. Sicotte, Arthur Toga
"... In PAGE 7: ... Again, the dataset was split in half for training and test- ing. Table1 (b) gives the detection rate for the lesion. The detection rate (recall) stresses the importance of picking up most of the lesion mass.... ..."
Cited by 1

TABLE 1. Graph Theoretic Measures for Evaluating Networks on Nonplanar Networks

in COMPARATIVE APPROACHES FOR ASSESSING NETWORK VULNERABILITY
by Tony H. Grubesic, Timothy C. Matisziw, Alan T. Murray, Diane Snediker

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 3-2. VLSI neural network Chips

in National Aeronautics and Space Administration PREFACE
by Giles E Crimi, Henry Verheggen, John Malinowski, Robert Malinowski, Robert Botta 1996
"... In PAGE 38: ...Table3 -1. Analog VLSI vs.... ..."

Table 3 . Mapping Knowledge Base into Neural Network

in A Hybrid Approach for Arabic Literal Amounts Recognition
by Labiba Souici-meslati, Mokhtar Sellami
"... In PAGE 11: ....2. Correspondences Between Rules and Neural Network In KBANN approach [20, 21], a symbolic explanation-based learner uses a roughly correct domain theory to explain why an example belongs to the target concept. The explanation tree (hierarchical knowledge base) produced is mapped into a neural network : this mapping, specified by Table3 , defines the topology of networks created by KBANN as well as their initial link weights. Table 3 .... ..."
Cited by 1

Table 1: Logit and Neural Network Forecasting Performance

in The Problem with Quantitative Studies of International Conflict
by Nathaniel Beck, Gary King, Langche Zeng
"... In PAGE 13: ... 4.2 Forecasts Table1 gives one view of the comparative forecasting performance of the logit and neural network (NN) models. In the table, we divide the forecasts into 1s (for con ict) and 0s (for peace).... In PAGE 14: ... Furthermore, most of these gures are lower than their t to the training set, which is as it should be if we expect structure to exist but some real change in the world to occur. Table1 demonstrates that the neural network model discriminates far better than the logit model by assigning very di erent probabilities of international con ict to the available dyads. It does not indicate whether either model apos;s probability values are correct except for above and below the 0.... In PAGE 15: ...4 bin. Whereas the left graph of Table1 evaluates the t of the two models to the same data, the right graph uses the same technique to evaluate the success of the out-of-sample forecasts. This graph shows a reasonably close correspondence again between the estimated probabilities and observed fractions for both models.... ..."

Table 11: Neural network based sampling results for the 2-regime mixture model (43)

in reduced rank models
by Lennart F. Hoogerheide, Johan F. Kaashoek, Herman K. Van Dijk 2004
"... In PAGE 23: ...05. Table11 and 12 show the results. Even after 25 million drawings IS and MH with the normal candidate distribution yield completely different results than the other algorithms.... ..."

Table 2: Final results for matching rect1 and rect2 by Similarity Flooding and Hopfield-style neural network.

in region
by Benedikt Fischer, Christian Thies, Mark O. Güld, Thomas M. Lehmann
"... In PAGE 6: ... In some cases, multiple possible matchings for regions were computed. As an example for a typical outcome, the final results of matching the graph of Figure 5, top row to the one of Figure 5, middle row, are provided in Table2 . Here, obviously the regions with the same color and size were matched onto each other correctly (mapping-pairs (2,3), (3,4), (4,5), (5,6), (6,8), (7,7), (10,10), and (11,9)).... In PAGE 7: ...istances are identical if query and range graph are swapped, i.e. it is independent of which graph is used as the query graph. The results for the example matching of rect1 and rect2 are summarized in Table2 . The mappings are identical to the ones obtained by Similarity Flooding except for the matchings (8, 11) and (9,12).... ..."

Table 1. Hopfield Neural Network Applications

in Hopfield Neural Networks—A Survey
by Humayun Karim Sulehria, Ye Zhang
"... In PAGE 4: ... The applications of HNN include image [25] and speech processing, control, signal processing, database retrieval, fault-tolerant computing, pattern classification and recognition [20], automatic target recognition [24], olfactory processing, knowledge processing, while for the analog version we have applications such as image and signal processing, control, olfactory processing, pattern recognition [24], and in combinatorial optimization [12] problems. Many applications of the HNN in industry are described in ( Table1 ) [18]. In [23], the application of HNN in automatic target recognition is reviewed.... ..."
Results 1 - 10 of 72,829