Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 12
Sivu 92
... proving the theorem , we shall show that the sequence S converges to a point P. - k For any fixed W in W let lim | Ŵ1⁄2 W | = 1 ( W ) ; 1 ( W ) exists since Eq . ( 5.38 ) holds for all k . We conclude that We must converge to a ...
... proving the theorem , we shall show that the sequence S converges to a point P. - k For any fixed W in W let lim | Ŵ1⁄2 W | = 1 ( W ) ; 1 ( W ) exists since Eq . ( 5.38 ) holds for all k . We conclude that We must converge to a ...
Sivu 93
... proved a generalized version of Theo- rem 5.1 in which the correction increment ck of Eq . ( 5-4 ) need not be independent of k . Theorem 5.2 was first proved by C. Kesler at Cornell University . Our proof is a version of Kesler's as it ...
... proved a generalized version of Theo- rem 5.1 in which the correction increment ck of Eq . ( 5-4 ) need not be independent of k . Theorem 5.2 was first proved by C. Kesler at Cornell University . Our proof is a version of Kesler's as it ...
Sivu 113
... proved that the fixed - increment error - correction training method implied a bound on the length of the weight vectors , thus explaining some cases in which the committee machine cannot be successfully trained . REFERENCES 1 Farley ...
... proved that the fixed - increment error - correction training method implied a bound on the length of the weight vectors , thus explaining some cases in which the committee machine cannot be successfully trained . REFERENCES 1 Farley ...
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 step subsidiary discriminant Suppose terns 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 |