Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 9
Sivu 62
... derivation is given by Minsky . Winder1 has determined that the weights specified by Eqs . ( 3-14 ) and ( 3-15 ) of this example will realize only a small percentage of the linearly separable switching functions and suggests another ...
... derivation is given by Minsky . Winder1 has determined that the weights specified by Eqs . ( 3-14 ) and ( 3-15 ) of this example will realize only a small percentage of the linearly separable switching functions and suggests another ...
Sivu 77
... derivation of L ( N , d ) given in the footnote on page 67 follows the derivation by Cameron , 12 The error - correction training procedures discussed in Sec . 4.3 stem from a variety of sources . The fixed - increment and absolute ...
... derivation of L ( N , d ) given in the footnote on page 67 follows the derivation by Cameron , 12 The error - correction training procedures discussed in Sec . 4.3 stem from a variety of sources . The fixed - increment and absolute ...
Sivu 109
... Derivation of a discriminant function for a layered machine It was mentioned in Sec . 6 · 1 that the discriminant functions of layered machines are piecewise linear . In this section , we shall verify this statement . Y Consider the ...
... Derivation of a discriminant function for a layered machine It was mentioned in Sec . 6 · 1 that the discriminant functions of layered machines are piecewise linear . In this section , we shall verify this statement . Y Consider the ...
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 |