### Table 2.1: Properties of some adaptive up and down procedures. Their difierent convergence levels can be used to estimate difierent threshold values on the psychometric function.

### Table 5: Performances of the online unsupervised adaptation of the system, for a soft adaptation, as a function of the MAP adaptation weight a6 .

2004

"... In PAGE 4: ...dded to the 2 minutes of initial enrollment, i.e. more than dou- bling the training data. The unsupervised online soft adaptation, taking into ac- count the a posteriori probability of the target for weighting the adaptation, provides very similar results (cf Table5 ). Dis- tributions of impostor scores and of true speaker scores were estimated by histograms on the NIST 2001 cellular data, lead- ing to the estimation of the probability a55 a15 a3 a32 a13a41a20 given the score a14a16a15 a13a18a17a19a3a21a20 .... ..."

Cited by 1

### Table 4.1: Spending on Maintenance of Social Assets by the Vladimir Tractor Plantin

"... In PAGE 17: ... But the attitude towards din0berent kinds of social activ- ities is the same. As one can see from Table4 , social functions associated with holding social assets are considered byenterprise managers as the most din0ecult ones. Social func- tions associated with provision of non-wage benen0cts including those in kind but which... In PAGE 18: ...transportation subsidies, direct distribution of commodities produced by the enterprise itself or received through barter at subsidized pricesn29 constitute a much less burden than the former ones. For example, Table4 shows that in general it is much more easy for en- terprises to compensate their workers for resort recreation in cash than to hold recreation facilities themselves. In addition, there is a din0berent attitude towards two din0berent groups of social assets.... In PAGE 52: ...Table4 : The Most and the Least Problematic Types of Benen0cts as Assessed byEnterprise Managers Among 3 of the Most Among 3 of the Most Din0ecult Benen0cts Easy Benen0cts to to Provide Provide Type of Benen0ct n28Number of Responsesn29 n28Number of Responsesn29 Kindergartens 15 0 Housing 10 0 Dormitories 7 0 Recreation facilities 5 0 Canteen with subsidized prices 5 3 Compensation for resort recreation 2 3 Sport facilities 2 4 Cultural center 1 0 Healthcare facilities 1 5 Food shop with subsidized prices 0 2 Transportation subsidy 0 2 Commodities on subsidized prices 0 6 Total number of responses: 24. Source: Enterprise survey.... ..."

### TABLE I HYPOTHESESAND PULSE SHAPESCORRESPONDINGTO FIG.2. The attenuation of the signal can be modeled by another multiplicative parameter AC, which is a function of AB and AR for Gaussian pulses; and AB and AS for exponential pulses. Once AR, AB, and AC are known, or adaptively estimated, they can be used in conjunction with receiver operating character- istic (ROC) curves to adaptively select the optimum signal de- tection threshold, AL, for minimizing the total error probability.

in An Adaptive Threshold Detector and Channel Parameter Estimator for Deep Space Optical Communications

### Table 1. Error Sum of Squares between Estimated and Observed Mean Value Functions

1996

"... In PAGE 4: ... Figure 4 gives the mean value functions for data set 1 (actual) and those estimated for the exponential and s- shaped and Weibull coverage functions. The error sum of squares between the predicted and ob- served mean value functions are summarized in Table1 . It is evident that the best approximation of the observed mean value function is achieved by different coverage functions for different data sets, in a least error sum of squares sense.... ..."

Cited by 6

### Table 1. Error Sum of Squares between Estimated and Observed Mean Value Func- tions

1996

"... In PAGE 7: ... Similarly, Figure 5 shows plots for the Weibull covearge function for various val- ues of . The error sum of squares for the various coverage functions and the data sets is sum- marized in Table1 . It is evident from Table 1 that the best approximation of the observed mean value function is achieved by di erent coverage functions for di erent data sets, in a least error sum of squares sense.... ..."

Cited by 6

### Table 1. Error Sum of Squares between Estimated and Observed Mean Value Func- tions

1996

Cited by 6

### Table 1. Error Sum of Squares between Estimated and Observed Mean Value Func- tions

1996

Cited by 6

### Table 2: Results for the algorithm applied to pose estimation. Here we used the parametrization function in (8). The corresponding weight matrices are shown in gure 3. We remark that in this case we used a kind of graph which was created for a di erent task: the segmentation of a face under the assumption that the pose is already known as described in [WFK]. Just by introducing weights in the discrimination function the errors could be reduced to the half. Here no ne tuning, like adding new nodes or selecting a special kind of gfk adapted to pose estimation, is done to increase the performance. This kind of work is still in progress and we will describe it more precisely in [KPM].

1997

"... In PAGE 7: ... In [Kru] more detailed results are discussed. Table2 gives the results for the learning of class dependent weights... ..."

Cited by 28