Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 16
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 92
Therefore , the sequence Sw must converge to a point on the boundary of W , proving the theorem . k € k E > 5.7 Bibliographical and historical remarks 3 The first proof of Theorem 5.1 was outlined by Rosenblatt.1 Subsequent proofs have ...
Therefore , the sequence Sw must converge to a point on the boundary of W , proving the theorem . k € k E > 5.7 Bibliographical and historical remarks 3 The first proof of Theorem 5.1 was outlined by Rosenblatt.1 Subsequent proofs have ...
Sivu 134
... 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 function , bivariate , 50 equations ...
... 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 function , bivariate , 50 equations ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
adjusted apply assume bank belonging 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 mean vector 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
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |