Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 12
Sivu 98
... dot products having the correct sign . Therefore these three weight vectors can be employed by a committee of three TLUs in such a Y1 W W2 1 Y2 W3 Y 3 FIGURE 6.3 A commmittee of weight vectors way that the consensus or majority of the ...
... dot products having the correct sign . Therefore these three weight vectors can be employed by a committee of three TLUs in such a Y1 W W2 1 Y2 W3 Y 3 FIGURE 6.3 A commmittee of weight vectors way that the consensus or majority of the ...
Sivu 100
... dot product with Y minus the number having a negative dot product with Y. * Thus , N is the sum operated on by the threshold of the vote - taking TLU . If the majority of the vectors W1 ( * ) , W1 ( k ) Wp ) have nonnegative dot products ...
... dot product with Y minus the number having a negative dot product with Y. * Thus , N is the sum operated on by the threshold of the vote - taking TLU . If the majority of the vectors W1 ( * ) , W1 ( k ) Wp ) have nonnegative dot products ...
Sivu 101
... dot products closest to zero . ( Ties are resolved arbitrarily . ) These , in one sense , are the easiest to adjust . The adjustment is achieved by the familiar process of adding ( or subtracting ) the pattern vector to ( or from ) the ...
... dot products closest to zero . ( Ties are resolved arbitrarily . ) These , in one sense , are the easiest to adjust . The adjustment is achieved by the familiar process of adding ( or subtracting ) the pattern vector to ( or from ) the ...
Sisältö
TRAINABLE PATTERN CLASSIFIERS | 1 |
PARAMETRIC TRAINING METHODS | 43 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
Tekijänoikeudet | |
3 muita osia ei näytetty
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
assume augmented pattern belonging to category Chapter cluster committee machine committee TLUS components correction increment covariance matrix d-dimensional decision surfaces denote diagonal matrix discussed dot products error-correction procedure Euclidean distance example Fix and Hodges 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 second layer 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 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 |