Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 20
Sivu 96
... machine . Layered machines can implement quite complex decision surfaces . We shall see later in this chapter that the decison surfaces of ... machines . In general , layered machines can be trained by varying 96 LAYERED MACHINES.
... machine . Layered machines can implement quite complex decision surfaces . We shall see later in this chapter that the decison surfaces of ... machines . In general , layered machines can be trained by varying 96 LAYERED MACHINES.
Sivu 104
... layer until the TLU in the last or Nth layer transforms the set g ( N - 1 ) of image points into the two vertices of a one - dimensional cube . These two vertices represent the two possible responses of the layered machine . Thus the ...
... layer until the TLU in the last or Nth layer transforms the set g ( N - 1 ) of image points into the two vertices of a one - dimensional cube . These two vertices represent the two possible responses of the layered machine . Thus the ...
Sivu 112
... layered machine is a piecewise linear machine . • · • A layered machine with P TLUS in the first layer has a total of 2P linear subsidiary discriminant functions ; these are divided into two classes ( corresponding to category 1 and ...
... layered machine is a piecewise linear machine . • · • A layered machine with P TLUS in the first layer has a total of 2P linear subsidiary discriminant functions ; these are divided into two classes ( corresponding to category 1 and ...
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 |