### Table 2: Test results for n = 10 classi ers in the pool and committees with odd numbers of members.

1998

"... In PAGE 12: ... Note that the linear programming bound is superior to the direct bound for every test. Table2 shows the results of 10 tests with pools of 10 classi ers. In each test, the odd-sized committee with minimum validation error was selected.... ..."

Cited by 10

### Table XIV Accuracy for chains with odd number of cysteines after a simple ranking mechanism is applied for the SVM prediction

### TABLE 3.2 Latin Square for Stimulus Presentation Order. Two Latin Squares are required because there is an odd number of treatments (5).

1997

Cited by 1

### Table 1: Learning the odd-number-of-ones grammar with a 2ORNN having 2 hidden neurons, with and without optimization of the initial state.

"... In PAGE 5: ...l. (1992a,b) in order to achieve learning in a reasonable number of epochs. This behavior has not been observed for other grammars. Table1 shows convergence results for a network with 2 hidden neurons and 2 or 3 input neurons. The third neuron is for an end-of-word symbol, used in the original model to compensate for the fact that an inadequate choice of the xed initial state may preclude a correct classi cation of the empty word and make the network too rigid.... ..."

### Table 2: TP(wx i(I)) = wy i(TP(I)) holds for the even and odd numbers program.

2004

Cited by 13

### Table 2: TP(wx i (I)) = wy i (TP(I)) holds for the even and odd numbers program.

2004

Cited by 13

### Table 1: Summary of RMS retrieval errors for both neural net and regression methods, for three channel sets. TIGR error is error retrieving odd numbered pro les. All retrievals are with AIRS instrument noise added.

1995

"... In PAGE 9: ...04K. Table1 and Figures 2, 3, and 4 give a summary of RMS error for both neural nets and regression, for several channel sets. Training (or regression) is performed on even-numbered TIGR pro les.... In PAGE 13: ... If ^ Tb is Tb with added noise, then let ^ Tb0 = BT 1 ^ Tb, let C be the least squares solution to C ^ T 0 b = T 0, and D = B2CBT 1 . Table1 and Figures 2, 3 and 4 summarize RMS testing error for the regression method, and compare regression results with neural nets. As with the neural nets, the eigenvector bases are determined from and the regression is performed on even-numbered TIGR pro les, while the error shown is for retrievals of the odd-numbered TIGR pro les.... In PAGE 21: ... In addition the adaptive learning rate variation of backprop that we used has several parameters: learning rate increment, decrement, and error threshold. Parameters for the adaptive learning algo- rithm, as used to train the 728-input net (run 410) described in Figure 2 and Table1 are as follows. Parameter Run 410 Useful Range momentum 0.... ..."

Cited by 1

### Table 1. Odds of winning

"... In PAGE 7: ... A seventh number is drawn, called a complementary number (or gold number or bonus number ) which, if found, allows already-winning players to enhance their gains. The odds of finding numbers matching winning numbers with or without the complementary number are indicated in Table1 , where the sign + indicates cases when the complemen- tary number is discovered. They are given for a typical purchase, that is a 8-grid tickets valid for two consecutive drawings the same day and for a cost... ..."

### Table 2: Numbers of circulant n-graphs, n odd

1996

"... In PAGE 34: ...n;; N) (see (6.1.1)). C 0 d (n) in Table2 denotes the number of n-circulants having no automorphism outside of Z(n). Their values (which are known only for prime n = p and are unexpectedly close to those of C t (n)) have been taken from [ChiL86].... ..."