Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 13
Sivu 84
Certainly k can be no larger than km , which is a solution to the equation or kmM = km = km2a2 W2 MW2 a2 ( 5.21 ) Therefore , we have proved ( for Ŵ1 = 0 ) that the fixed - increment error - correction procedure must terminate ...
Certainly k can be no larger than km , which is a solution to the equation or kmM = km = km2a2 W2 MW2 a2 ( 5.21 ) Therefore , we have proved ( for Ŵ1 = 0 ) that the fixed - increment error - correction procedure must terminate ...
Sivu 109
... vertex belonging to 2 ( 1 ) ( 6 · 10 ) Since ✩ has an inverse ( it has rank equal to P ) , we can always solve for w by W = CM - 1 ( 6.11 ) Thus , since a threshold and weight vector can always be found , the theo- rem is proved .
... vertex belonging to 2 ( 1 ) ( 6 · 10 ) Since ✩ has an inverse ( it has rank equal to P ) , we can always solve for w by W = CM - 1 ( 6.11 ) Thus , since a threshold and weight vector can always be found , the theo- rem is proved .
Sivu 116
Since the piecewise linear discriminant functions are not functions , the error - correction training theorems proved in Chap- ter 5 do not apply to PWL machines . The pattern capacity of PWL ma- chines is also unknown .
Since the piecewise linear discriminant functions are not functions , the error - correction training theorems proved in Chap- ter 5 do not apply to PWL machines . The pattern capacity of PWL ma- chines is also unknown .
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
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 |
Kirjaluettelon tiedot
| Otsikko | Learning Machines: Foundations of Trainable Pattern-classifying Systems McGraw-Hill series in systems science |
| Kirjoittaja | Nils J. Nilsson |
| Painos | kuvitettu |
| Kustantaja | McGraw-Hill, 1965 |
| ISBN | 0070465703, 9780070465701 |
| Pituus | 137 sivua |
| Vie sitaatti | BiBTeX EndNote RefMan |