Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 20
Sivu 66
... Weight space Before discussing training methods for a TLU it will be helpful to formu- late a geometric representation in which the TLU weight values are the coordinates of a point in a multidimensional space . This space , which we ...
... Weight space Before discussing training methods for a TLU it will be helpful to formu- late a geometric representation in which the TLU weight values are the coordinates of a point in a multidimensional space . This space , which we ...
Sivu 70
... weight vector W responds incorrectly to an augmented pattern vector Y. The weight vec- tor is then changed to a new ... point W and the pattern hyperplane corresponding to Y. The quantity WY W ' . Y is then proportional to the distance ...
... weight vector W responds incorrectly to an augmented pattern vector Y. The weight vec- tor is then changed to a new ... point W and the pattern hyperplane corresponding to Y. The quantity WY W ' . Y is then proportional to the distance ...
Sivu 71
... weight point Final weight point 4 FIGURE 4.2 A graphical illustration of error - correction training X guarantee that the pattern hyperplane is crossed and the response cor- rected . In the third case c is so chosen that the distance ...
... weight point Final weight point 4 FIGURE 4.2 A graphical illustration of error - correction training X guarantee that the pattern hyperplane is crossed and the response cor- rected . In the third case c is so chosen that the distance ...
Sisältö
TRAINABLE PATTERN CLASSIFIERS | 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 called cells changes Chapter cluster column committee machine components consider consists contains correction corresponding covariance decision surfaces define denote density depends described dichotomies discriminant functions discussed distance distributions elements equal error-correction estimates example exist expression FIGURE fixed given implemented important initial layered machine linear machine linearly separable lines majority matrix mean measurements modes negative networks nonparametric normal Note optimum origin parameters partition pattern classifier pattern hyperplane pattern space pattern vector piecewise linear plane points positive presented probability problem properties PWL machine quadric regions respect response rule selection separable sequence side solution space Stanford step subsidiary discriminant Suppose theorem theory threshold training methods training patterns training procedure training sequence training subsets transformation values weight vectors X1 and X2 Y₁ zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |