### Table 4: Test set scores for the combination of a neural translation model (TM) and a neural language model (LM).

"... In PAGE 7: ... The neural translation and target language model were also applied to the test data, using of course the same feature function coefficients as for the devel- opment data. The results are given in Table4 for all the official measures of the IWSLT evaluation. The new smoothing method of the translation probabili- ties achieves improvement in all measures.... ..."

### Table 4: Neural network tools.

2003

"... In PAGE 20: ... They are applicable in almost every situation where a relationship between input and output parameters exists, even in cases where this relationship is very complex and cannot be expressed or handled by mathematical or other modelling means. Table4 summarizes the features of the most commonly used neural network tools. Beyond general purpose and stand-alone tools, there exist library tools, such as the SPRLIB and the ANNLIB (developed by the Delft University Technology at Netherlands) emphasizing on image classification and pattern recognition applications.... ..."

Cited by 2

### Table 9: Comparison of the adapted neural network model and the supervised network model.

"... In PAGE 18: ..., 1993) using the ADINUL collection. Table9 and Figure 2(b) show the precision-recall comparison between our neural network and the supervised neural network. In this comparison, it can be seen that the retrieval performance of the supervised neural network is slightly better than that of our network.... ..."

### Table 1. Models of the mass distribution in NGC 5907

"... In PAGE 3: ... The model of mass dis- tribution in NGC 5907 we used is similar to that described in [26] (see also [18]). Table1 gives parame- ters of the main galaxy for our three cases. In all cases, the rotation curve has a flat portion in the range 8 to 30 kpc (Fig.... In PAGE 6: ... 26 No. 5 2000 RESHETNIKOV, SOTNIKOVA In model 2 ( Table1 ), the potential of the halo corre- sponds to the potential of a standard isothermal sphere with infinite total mass. In order that the total mass of dark matter within the region of companion motion (~52 kpc) be approximately the same as that in model 1, we reduced the halo mass within Ropt.... In PAGE 6: ... 4a and 4b is also formed in this case. It also follows from our computations that model 3 ( Table1 ) is unacceptable. In this model, the mass of the halo within the region of companion motion is consid- erably higher than that in models 1 and 2.... ..."

### 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 2 Comparison between neural network models and the linear model

"... In PAGE 4: ... This is particularly true when we consider the fact that no patient specific attributes (age, weight, gender, race) were utilized in the analysis. A comparison of the errors produced by all the models is presented in Table2 . Mean values and Standard Deviations of RMSE and NRMSE over whole patient population are shown.... ..."