Learning Machines: Foundations of Trainable Pattern-classifying SystemsMcGraw-Hill, 1965 - 137 sivua |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 13
Sivu 97
... machine . In the next three sections , we shall discuss a method in which only the TLUs in one layer of the network are trained . 6.2 Committee machines Suppose we have training subsets Y1 and Y2 of augmented training pat- terms which ...
... machine . In the next three sections , we shall discuss a method in which only the TLUs in one layer of the network are trained . 6.2 Committee machines Suppose we have training subsets Y1 and Y2 of augmented training pat- terms which ...
Sivu 98
... committee " of weight vectors W1 , W2 , and W3 in Fig . 6.3 . With respect to these weight vectors , we have the inequalities W1 1 W1 . Y1 > 0 W1 · Y2 > 0 • 2 W1 Y3 > 0 W2 . Y2 > 0 2 W2 . Y3 < 0 ( 6.4 ) W3 . Y1 > 0 W3 . Y2 < 0 2 W3 Y3 ...
... committee " of weight vectors W1 , W2 , and W3 in Fig . 6.3 . With respect to these weight vectors , we have the inequalities W1 1 W1 . Y1 > 0 W1 · Y2 > 0 • 2 W1 Y3 > 0 W2 . Y2 > 0 2 W2 . Y3 < 0 ( 6.4 ) W3 . Y1 > 0 W3 . Y2 < 0 2 W3 Y3 ...
Sivu 99
... committee machine with a fixed vote - taking TLU . * 1 x X Response Vote - taking TLU ( second layer ) Pattern = +1 d + 1 P committee TLUS ( first layer ) FIGURE 6.4 A committee machine 6.3 A training procedure for committee machines ...
... committee machine with a fixed vote - taking TLU . * 1 x X Response Vote - taking TLU ( second layer ) Pattern = +1 d + 1 P committee TLUS ( first layer ) FIGURE 6.4 A committee machine 6.3 A training procedure for committee machines ...
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 |