Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 14
Sivu 89
Proof The proof of Theorem 5.2 is accomplished by reformulating the R - category problem as a dichotomy problem in a higher - dimensional space and then applying Theorem 5.1 . The first step is to generate a new set Z of higher ...
Proof The proof of Theorem 5.2 is accomplished by reformulating the R - category problem as a dichotomy problem in a higher - dimensional space and then applying Theorem 5.1 . The first step is to generate a new set Z of higher ...
Sivu 108
Proof > We have P TLUs , each of which implements a hyperplane in the pattern space . In this proof it will be convenient for the TLUs to have 0 , 1 responses rather than -1 , 1 responses . Since exactly P + 1 cells are occupied by ...
Proof > We have P TLUs , each of which implements a hyperplane in the pattern space . In this proof it will be convenient for the TLUs to have 0 , 1 responses rather than -1 , 1 responses . Since exactly P + 1 cells are occupied by ...
Sivu 134
... 126 Fix and Hodges method , 120 , 125 Fixed - increment rule , 70 proof of convergence of , 82 , 85 Fractional correction rule , 70 , 91 proof of convergence of , 91 Fundamental training theorem , 79 > Gaussian probability - density ...
... 126 Fix and Hodges method , 120 , 125 Fixed - increment rule , 70 proof of convergence of , 82 , 85 Fractional correction rule , 70 , 91 proof of convergence of , 91 Fundamental training theorem , 79 > Gaussian probability - density ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Sisältö
I | 1 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
APPENDIX | 127 |
Tekijänoikeudet | |
1 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 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 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 specific Stanford step Suppose theorem theory threshold training methods training patterns training procedure training sequence training subsets transformation values weight vectors zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |