Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 19
Sivu 96
... machine . Layered machines can implement quite complex decision surfaces . We shall see later in this chapter that the decison surfaces of layered ... 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 layered ... 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 110
... machine for R = 2. Suppose the first layer has P TLUS . Let the binary output of the ith TLU in the first layer be denoted by u . , and let the weight vector corresponding to this TLU be denoted by W ... layered machines. 110 LAYERED ...
... machine for R = 2. Suppose the first layer has P TLUS . Let the binary output of the ith TLU in the first layer be denoted by u . , and let the weight vector corresponding to this TLU be denoted by W ... layered machines. 110 LAYERED ...
Sisältö
TRAINABLE PATTERN CLASSIFIERS | 1 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
LAYERED MACHINES | 95 |
Tekijänoikeudet | |
1 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 dot products error-correction procedure Euclidean distance example Fix and Hodges function g(X g₁(X gi(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 vector 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 |