Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 12
Sivu 103
... Transformation properties of layered machines We have seen in Secs . 6.2 to 6-4 that the concept of the first - layer TLUS as voters in a " committee " is a productive representation for two - layer machines . Another representation ...
... Transformation properties of layered machines We have seen in Secs . 6.2 to 6-4 that the concept of the first - layer TLUS as voters in a " committee " is a productive representation for two - layer machines . Another representation ...
Sivu 104
... transform each of the I1 - space vertices into one of the vertices of a P2 - dimensional hypercube . The transformation from I1 space to I2 space depends on the values of the weights in the second layer . For a given set of weights ...
... transform each of the I1 - space vertices into one of the vertices of a P2 - dimensional hypercube . The transformation from I1 space to I2 space depends on the values of the weights in the second layer . For a given set of weights ...
Sivu 131
... transformation where Using Eq . ( A - 14 ) we have Ꮓ = QX Q = DtTt ( A.13 ) ( A ∙ 14 ) 1 p ( X ) = ( 2π ) d / 22 exp [ -12 ( Z - QM ) ( Z — QM ) ] - ( A.15 ) Equation ( A - 15 ) suggests that the vector Z = QX is a normal pat- tern ...
... transformation where Using Eq . ( A - 14 ) we have Ꮓ = QX Q = DtTt ( A.13 ) ( A ∙ 14 ) 1 p ( X ) = ( 2π ) d / 22 exp [ -12 ( Z - QM ) ( Z — QM ) ] - ( A.15 ) Equation ( A - 15 ) suggests that the vector Z = QX is a normal pat- tern ...
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
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 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 theorem theory threshold training methods training patterns training procedure training sequence training subsets transformation values weight vectors X1 and X2 Y₁ zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |