Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 5
Sivu 104
... image space or the I1 space . The trans- formation between the pattern space and the I space depends on the values of the weights in the first layer . For a given set of weights , the first layer will transform a finite set X of pattern ...
... image space or the I1 space . The trans- formation between the pattern space and the I space depends on the values of the weights in the first layer . For a given set of weights , the first layer will transform a finite set X of pattern ...
Sivu 105
... image - space cube in accordance with the TLU 5 TLU 3 6 8 6 TLU 1 TLU 2 Origin * 1 ( a ) Pattern space 3 x2 1,4,5,8 3,7 TLU 3 ! Origin TLU 2 -- * TLU 1 ( b ) Image space 2 FIGURE 6 6 Pattern - space to image - space transformation ...
... image - space cube in accordance with the TLU 5 TLU 3 6 8 6 TLU 1 TLU 2 Origin * 1 ( a ) Pattern space 3 x2 1,4,5,8 3,7 TLU 3 ! Origin TLU 2 -- * TLU 1 ( b ) Image space 2 FIGURE 6 6 Pattern - space to image - space transformation ...
Sivu 106
... space TLU 1 ( b ) Image space FIGURE 6.7 Transformations in a two - layer machine the pattern space into cells such that no two patterns of opposite cate- gorization reside in the same cell . The necessity for partitioning the sets X1 ...
... space TLU 1 ( b ) Image space FIGURE 6.7 Transformations in a two - layer machine the pattern space into cells such that no two patterns of opposite cate- gorization reside in the same cell . The necessity for partitioning the sets X1 ...
Sisältö
Preface vii | 11 |
PARAMETRIC TRAINING METHODS | 43 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
Tekijänoikeudet | |
5 muita osia ei näytetty
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
adjusted apply assume bank called cells changes Chapter classifier cluster column committee machine components consider consists contains correction corresponding covariance decision surfaces define denote density depends described discriminant functions discussed distance distributions elements equal error-correction estimates example exist expression FIGURE fixed given implemented important initial layered machine linear machine linearly separable lines majority matrix mean measurements modes negative networks nonparametric normal Note optimum origin parameters partition pattern hyperplane pattern space pattern vector pattern-classifying piecewise linear plane points positive presented probability problem properties PWL machine quadric regions respect response rule selection separable sequence side solution space Stanford step subsidiary discriminant Suppose terns theorem theory threshold training methods training patterns training procedure training sequence training subsets transformation values weight vectors Y₁ zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |