Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 13
Sivu 84
... proved ( for Ŵ1 = 0 ) that the fixed - increment error - correction procedure must terminate after at most km steps ... proving the theorem , the bound itself is not very useful in estimating how many steps will be required in a given ...
... proved ( for Ŵ1 = 0 ) that the fixed - increment error - correction procedure must terminate after at most km steps ... proving the theorem , the bound itself is not very useful in estimating how many steps will be required in a given ...
Sivu 109
... proved . Note that there is a great amount of freedom allowed in finding a solution vector w . After the threshold value is chosen , the quantities c ; can be chosen arbitrarily within the constraints given by Eq . ( 6 · 10 ) . One ...
... proved . Note that there is a great amount of freedom allowed in finding a solution vector w . After the threshold value is chosen , the quantities c ; can be chosen arbitrarily within the constraints given by Eq . ( 6 · 10 ) . One ...
Sivu 116
... proved in Chap- ter 5 do not apply to PWL machines . The pattern capacity of PWL ma- chines is also unknown . Even though well - developed theory is lacking , some speculations have been advanced that we shall discuss . 7.2 Training PWL ...
... proved in Chap- ter 5 do not apply to PWL machines . The pattern capacity of PWL ma- chines is also unknown . Even though well - developed theory is lacking , some speculations have been advanced that we shall discuss . 7.2 Training PWL ...
Sisältö
TRAINABLE PATTERN CLASSIFIERS | 1 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
TRAINING THEOREMS | 79 |
Tekijänoikeudet | |
2 muita osia ei näytetty
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
adjusted apply assume bank called cells changes Chapter cluster column committee machine components consider consists contains correction corresponding covariance decision surfaces define denote density depends described dichotomies 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 classifier pattern hyperplane pattern space pattern vector 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 |