### Table 1. Cellular networks as drug target maps.

"... In PAGE 2: ... In cellular networks the interacting molecules are considered as the elements, and their interactions form the weighted, but not necessarily directed links of the respective structural network. Alternatively, we may also envision directed links as representations of signalling or metabolic processes of the functional networks in the cell ( Table1 . [27-29]).... ..."

### Table 3 . Mapping Knowledge Base into Neural Network

"... 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 6: Neural network results.

"... In PAGE 5: ... Figure 5: Signal space for neural network. Table6 shows that the network using the 7- signal characteristic set gave the correct result 93.... ..."

### Table 3-2. VLSI neural network Chips

1996

"... In PAGE 38: ...Table3 -1. Analog VLSI vs.... ..."

### Table 1: Best neural networks obtained using random dynamic neighborhoods.

"... In PAGE 6: ... Nevertheless, the best random dynamic neighborhood configuration from Ta- ble 1 produced a better generalizer than the best from Table 2, and further experiments confirmed this statistically. Figure 15 shows how generalization performance behaved in relation to k for both levels of n (20 and 30) for the top-4 NN architectures from Table1 . There is a peak in perfor- mance in the region of k=4,5.... ..."

### Table 2 Calcium isotope abundances and interferences in human urine

2001

"... In PAGE 3: ... Results and discussion Spectral interferences When analysing urine using sector field ICP-MS, all the calcium isotopes are overlapped by polyatomic ions and/or doubly charged ions at low resolution. In Table2 , the natural abundance of the calcium isotopes, the most commonly encountered interferences and the mass resolution needed to resolve these from the analyte peaks are presented. The 42Ca, J.... ..."

### Table 1 Neural network architectures

2003

"... In PAGE 6: ...etter as the scale is increased, i.e. as the data becomes smoother. On the final smooth trend curve, resid(t)in Table1 , a crude linear extrapolation estimate, i.e.... In PAGE 6: ...avelet coefficients at higher frequency levels (i.e. lower scales) provided some benefit for estimating variation at less high frequency levels. Table1 sum- marizes what we did, and the results obtained. DRNN is the dynamic recurrent neural network model used.... In PAGE 6: ...sed. The architecture is shown in Fig. 3. The memory order of this network is equivalent to applying a time- lagged vector of the same size as the memory order. Hence the window in Table1 is the equivalent lagged vector length. In Table 1, NMSE is normalized mean squared error, DVS is direction variation symmetry (see above), and DS is directional symmetry, i.... In PAGE 6: ... Hence the window in Table 1 is the equivalent lagged vector length. In Table1 , NMSE is normalized mean squared error, DVS is direction variation symmetry (see above), and DS is directional symmetry, i.e.... In PAGE 7: ...ion of these results can be found in Ref. [4]. For further work involving the DRNN neural network resolution scale. From Table1 , we saw how these windows were of effective length 10, 15, 20, and 25 in terms of inputs to be considered. Fig.... ..."

### Table 3.1. CSRC Optical Flow Algorithm Mapping

1998

Cited by 1

### Table 2 Configuration and performance assessment in mapping the Mode Shape using GP, Neural Network and Polynomial model

2005

"... In PAGE 9: ...ig. 10 shows the performance of all models on the mode shape data. The mode shape data appears to be a challenge for all the methods to try fitting a metamodel. As shown in Table2 , all the surrogate models have become more complicated. However, it is worthwhile to note that both the Polynomial and Neural Network models have used all the input variables (nine stiffness parameters mentioned in the earlier section) to perform the metamodelling; while the GP only used 7 out of the 9 variables, which showed that the GP could identify the most influential design variables with respect to the output.... ..."

### Table 1 Mapping solutions of FlowMap-r.3

1994

"... In PAGE 21: ... These initial networks are synthesized using a MIS script [2] which performs technology independent optimization. Table1 shows the mapping solution sets computed by FlowMap-r. The time in this table is the CPU time used for the solution of the maximum depth relaxation shown in the table, recorded on a SUN SPARC IPC (14.... ..."

Cited by 69