Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 10
Sivu 22
... wa + 1 , can be provided by a weight whose value wa + 1 is energized by a signal of +1 . Usually this +1 signal is associated with the pattern as a ( d + 1 ) st input xa + 1 , whose value is always equal to +1 . Because the TLU ...
... wa + 1 , can be provided by a weight whose value wa + 1 is energized by a signal of +1 . Usually this +1 signal is associated with the pattern as a ( d + 1 ) st input xa + 1 , whose value is always equal to +1 . Because the TLU ...
Sivu 23
... wa + 1 / | w | . ( If Aw > 0 , the origin is on the positive side of the hyperplane . ) The equation X⚫n + Aw = 0 ... 1 ( W1X1 + W2X2 + + Waxa + Wa + 1 ) w ; 2 From our expressions for n and A , we note the following special cases ...
... wa + 1 / | w | . ( If Aw > 0 , the origin is on the positive side of the hyperplane . ) The equation X⚫n + Aw = 0 ... 1 ( W1X1 + W2X2 + + Waxa + Wa + 1 ) w ; 2 From our expressions for n and A , we note the following special cases ...
Sivu 49
... ( 1 ) and 1 — p ( 1 ) affect only the value of wa + 1 . As category 1 becomes less probable a priori , wa + 1 decreases . Such a decrease of wa + 1 favors a category 2 response for all patterns . - - Pi qi Note also that the ith weight w ...
... ( 1 ) and 1 — p ( 1 ) affect only the value of wa + 1 . As category 1 becomes less probable a priori , wa + 1 decreases . Such a decrease of wa + 1 favors a category 2 response for all patterns . - - Pi qi Note also that the ith weight w ...
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 |