Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 15
Sivu 102
Consider the three pattern vectors and their corresponding pattern hyperplanes (
lines ) shown in Fig . 6 - 5 . The arrows indicate the positive sides of the lines . In
this figure is shown the history of weight - vector adjustments produced by ...
Consider the three pattern vectors and their corresponding pattern hyperplanes (
lines ) shown in Fig . 6 - 5 . The arrows indicate the positive sides of the lines . In
this figure is shown the history of weight - vector adjustments produced by ...
Sivu 106
The pattern points for this example are shown in Fig . 6 · 7a . In this figure the
points marked represent patterns belonging to X1 , and the points marked o
represent patterns belonging to X2 . Clearly the TLUs in the first layer of the
desired ...
The pattern points for this example are shown in Fig . 6 · 7a . In this figure the
points marked represent patterns belonging to X1 , and the points marked o
represent patterns belonging to X2 . Clearly the TLUs in the first layer of the
desired ...
Sivu 108
Some examples of nonredundant and redundant partitions are shown in Fig . 6 .
8 . Note that the partition shown in Fig . 67a is also nonredundant . A
nonredundant partition is not necessarily one that uses a minimum number of
hyperplanes ...
Some examples of nonredundant and redundant partitions are shown in Fig . 6 .
8 . Note that the partition shown in Fig . 67a is also nonredundant . A
nonredundant partition is not necessarily one that uses a minimum number of
hyperplanes ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Sisältö
Preface vii | 1 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
TRAINING THEOREMS | 79 |
Tekijänoikeudet | |
2 muita osia ei näytetty
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
adjusted apply assume bank belonging to category called changes Chapter cluster committee components consider consists contains correction corresponding covariance decision surfaces define denote density depends derivation described Development discriminant functions discussed distance distribution element equal error-correction estimates example exists expression FIGURE fixed given implemented important initial layered machine linear dichotomies linear machine linearly separable matrix measurements negative networks normal Note optimum origin parameters partition pattern classifier pattern hyperplane pattern space pattern vector piecewise linear plane points positive presented probability problem proof properties proved PWL machine quadric reduced regions respect response rule sample mean selection separable shown side solution space Stanford step Suppose theorem theory threshold training methods training procedure training sequence training subsets transformation values weight vectors zero