### Table 1. Prediction Errors for

1998

"... In PAGE 4: ... For RSOM and MLP models length of the the input vector was varied as p 2f3;; 5;; 7g. The sum-squared errors gained for one-step prediction task are shown in Table1 . MLP(3,1,7) model gives the smallest cross-validation error but fails to predict the test set accurately.... ..."

Cited by 18

### Table 2. Prediction Errors for

1998

"... In PAGE 5: ... For RSOM and MLP models length of the the input vector was varied as p 2f3;; 5;; 7g. The sum-squared errors gained for one-step prediction task are shown in Table2 . The laser series is highly nonlinear and thus the errors gained with AR(12) model are considerably higher than for other models.... ..."

Cited by 18

### Table 3. Prediction errors

### Table 2: Phone prediction errors.

1992

"... In PAGE 2: ...Table 2: Phone prediction errors. Table2 summarizes the phone predictions. Substitutions account for 14% of the errors, with the most common sub- stitutions between /z/ and /s/, and between /e/ and /E/.... ..."

Cited by 2