### Table 2: One single step ahead vs. several steps ahead optimization

"... In PAGE 22: ... The robots paths are qualitatively more complex when more than one step are used in the optimization. Table2 shows quantitative results in terms of path properties and number of sensing locations. In general, the results are better with a totally greedy exploration.... ..."

### Table 1. Parameters used for evolutionary design of artificial neural networks

### Table 2. Global distortion along the image sequence for the Artificial Neural Network in the

"... In PAGE 7: ... In table 1 we show the results of the Evolutionary Algorithms with several parameter settings: population size, number of offsprings allowed and frequency of interaction (number of generations computed between environment interactions). Table2 shows the results for the inherently adaptive algorithms: the Artificial Neural Networks and our Evolution Strategy. In the case of the Artificial Neural Networks we have applied them using the Euclidean distance and a penalized distance to compute the winner.... ..."

### Table 1: Backpropagation artificial neural network versus regression.

"... In PAGE 11: ... 4. Results and Discussion Results for the baseline performance of the best performing two hidden layer backpropagation neural network using all eight input variable values and the rhythmicity regression equation are shown in Table1 . Accuracy is the total percentage of correct predictions.... In PAGE 12: ...3.6 percent classification accuracy is established by two of the seven variable models. Because the sharpness variable produced the largest decrease in classification performance when it was left out, a regression model using just the sharpness variable is constructed to determine the correlation between sharpness and epileptiform seizures and another regression model using both the sharpness and physiologic state (the second largest performance decrease) is also constructed. Both of these new regression models have a smaller accuracy than the original rhythmicity regression model (shown in Table1 ), with the sharpness regression model... ..."

### Table 3 Individual participant artificial neural network correlationsa

"... In PAGE 15: ...for model based on both sessions; RWB, session-B correlation for model based on both sessions. correlations of estimated to actual tracking performance time series for individual- session and across-session neural network models are shown in Table3 . Individual neural net models produced within- and cross-session mean correlations (R) of 0.... In PAGE 15: ...nd 0.62, and mean RMS errors of 1.04 and 1.96 disk radii, respectively. Also shown in Table3 are correlations of estimated to actual tracking performance based on individualized neural networks trained on data from both sessions (trained using the process described previously) for each participant. These models yielded a mean correlation (R) of 0.... ..."

### Table I. Timing Data Running Pyro on a Dual Pentium III 800 MHz Linux PC Pyro program and graphics Updates/second

2003

Cited by 14

### Table 1: Comparison of Artificial Immune Systems to Genetic Algorithms and Neural Networks.

2006

Cited by 10