Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 27
Sivu 81
... theorem can also be proved quite simply as a result of Theorem 5.1 . In the modified theorem we use an absolute error- correction procedure instead of the fixed - increment error - correction pro- cedure . In the absolute error ...
... theorem can also be proved quite simply as a result of Theorem 5.1 . In the modified theorem we use an absolute error- correction procedure instead of the fixed - increment error - correction pro- cedure . In the absolute error ...
Sivu 84
... theorem . Other than the fact that a bound on the number of steps exists , thus proving the theorem , the bound itself is not very useful in estimating how many steps will be required in a given situation ... Theorem 5 · 84 TRAINING THEOREMS.
... theorem . Other than the fact that a bound on the number of steps exists , thus proving the theorem , the bound itself is not very useful in estimating how many steps will be required in a given situation ... Theorem 5 · 84 TRAINING THEOREMS.
Sivu 93
... Theorem 5.2 was first proved by C. Kesler at Cornell University . Our proof is a version of Kesler's as it was related to the author during discussions in July , 1963 . 8 Theorem 5.3 is a slightly modified version of a theorem by ...
... Theorem 5.2 was first proved by C. Kesler at Cornell University . Our proof is a version of Kesler's as it was related to the author during discussions in July , 1963 . 8 Theorem 5.3 is a slightly modified version of a theorem by ...
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 |