### Table 1: Parameters of the adaptive algorithm.

2006

"... In PAGE 6: ...2 Parameter search Now that we have chosen a parameterized adaptive algo- rithm and have a means of generating bidder behavior, we are ready to search for the set of parameters that results in the best expected performance. (For reference, all parame- ters are described in Table1 .) For any given set of parameter values, we can obtain an estimate of the expected revenue from an episode by generating a population of bidders as described in Section 3.... ..."

Cited by 2

### Table 1: Parameters of the adaptive algorithm.

"... In PAGE 6: ...2 Parameter search Now that we have chosen a parameterized adaptive algo- rithm and have a means of generating bidder behavior, we are ready to search for the set of parameters that results in the best expected performance. (For reference, all parame- ters are described in Table1 .) For any given set of parameter values, we can obtain an estimate of the expected revenue from an episode by generating a population of bidders as described in Section 3.... ..."

### TABLE I ADAPTATION ALGORITHM SUMMARY

2003

Cited by 6

### TABLE 5. Adaptive algorithm perfor-

2007

### Table 1 Adaptation algorithm design space.

"... In PAGE 6: ... 3 Adaptation Control Algorithm Design Space In the remaining sections we discuss control algorithms for saving energy for adaptive general-purpose processors running real-time multimedia applications. Table1 summarizes the control algorithm design space as discussed in Section 1. The next few sections describe our LL, GG, GG+LL, and LG algorithms.... ..."

### Table 1 Adaptation algorithm design space.

"... In PAGE 6: ... 3 Adaptation Control Algorithm Design Space In the remaining sections we discuss control algorithms for saving energy for adaptive general-purpose processors running real-time multimedia applications. Table1 summarizes the control algorithm design space as discussed in Section 1. The next few sections describe our LL, GG, GG+LL, and LG algorithms.... ..."

### Table 1. Adaptation algorithm parameters GA

1998

"... In PAGE 4: ...ion, , three values were selected, 0.15, 0.00 and 0.30, and combined with a credit constant, = 0:5, these are denoted GA1, GA2 and GA3 in Table1 . The lev- els in GA1 are those that have been used by the author on speci c applications [2, 3]; in GA2, the adaptation algorithm is completely deactivated, as with = 0:00, the initial operator probabilities will remain unchanged for the entire run; GA3 represents a higher than usual rate of adaptation.... In PAGE 4: ... = 0:15), and set to 0.5, 0.0 and 1.0 in GA1, GA4 and GA5 respectively ( Table1 ). While the usual value of = 0:5 allows reasonable credit to parent and grand- parent operators, in GA4, credit is only awarded to the actual operator responsible for an improvement, whereas in GA5, the operator, parent and grandparent operators are all rewarded equally.... ..."

Cited by 4

### Table 1: Filter weights obtained by the adaptive algorithms.

"... In PAGE 19: ... The desired signal d(n) was obtained by passing s(n) through an FIR lowpass lter of window length N = 11, designed for a cuto frequency !c = 50. The weights of the designed lter are shown in Table1 , in the column entitled `Lowpass FIR apos;. Fig.... In PAGE 21: ... The step-sizes for the linear lter ( = 1:0 10?4) and the weighted median lter ( = 5:0 10?3) were chosen so that these algorithms converged in approximately the same number of iterations as the fastest weighted myriad lter algorithm (which was Algorithm II). The nal lter weights obtained by the various algorithms are shown in Table1 . The three weighted myriad lter algorithms converged to approximately the same weight vectors.... ..."