Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 17
Sivu 82
... proof of Theorem 5.1 is further simplified if we omit from the training sequence Sy any patterns Y for which W + 1 ... Proof 1 The following proof results from conflicting bounds on the growth rate of the length of the weight vector ...
... proof of Theorem 5.1 is further simplified if we omit from the training sequence Sy any patterns Y for which W + 1 ... Proof 1 The following proof results from conflicting bounds on the growth rate of the length of the weight vector ...
Sivu 92
... proof of Theorem 5.1 was outlined by Rosenblatt.1 Subsequent proofs have been given by Joseph , 2 Block , Charnes , Novikoff , " Single- ton , Ridgway , ' and possibly others . Our Proof 1 follows the method * Since Sŵ terminates when Ŵ ...
... proof of Theorem 5.1 was outlined by Rosenblatt.1 Subsequent proofs have been given by Joseph , 2 Block , Charnes , Novikoff , " Single- ton , Ridgway , ' and possibly others . Our Proof 1 follows the method * Since Sŵ terminates when Ŵ ...
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 ...
Sisältö
Preface vii | 1 |
PARAMETRIC TRAINING METHODS | 43 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
Tekijänoikeudet | |
4 muita osia ei näytetty
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
assume belonging to category Chapter cluster committee machine committee TLUS components correction increment covariance matrix decision surfaces denote diagonal matrix discussed dot products error-correction procedure Euclidean distance example Fix and Hodges function g(X g₁(X given Hodges method hypersphere image-space implemented initial weight vectors ith bank layer of TLUS layered machine linear dichotomies linear discriminant functions linearly separable loss function mean vector minimum-distance classifier mode-seeking networks nonparametric number of patterns p₁ parameters parametric training partition pattern hyperplane pattern points pattern space pattern vector pattern-classifying patterns belonging perceptron piecewise linear plane point sets positive probability distributions prototype pattern PWL machine quadratic form quadric function rule sample covariance matrix shown in Fig solution weight vectors Stanford subsets X1 subsidiary discriminant functions Suppose terns training patterns training sequence training set training subsets transformation two-layer machine values W₁ wa+1 weight point weight space weight-vector sequence X1 and X2 zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |