Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 9
Sivu 8
The sign of g ( x ) can be evaluated by a threshold element whose threshold
value is equal to zero . For this reason the threshold element assumes an
important role in pattern - classifying machines . We shall use the block diagram
of Fig . 1 .
The sign of g ( x ) can be evaluated by a threshold element whose threshold
value is equal to zero . For this reason the threshold element assumes an
important role in pattern - classifying machines . We shall use the block diagram
of Fig . 1 .
Sivu 21
The decision regions R , and R2 are separated by a hyperplane decision surface
defined by g ( x ) = 0 . Discriminant g ( x ) = ? wix ; twd + 1 i = 1 * ny Tw + 1 or - 1
Response Summing device Threshold element x : Pattern wd + 1 + 1 ...
The decision regions R , and R2 are separated by a hyperplane decision surface
defined by g ( x ) = 0 . Discriminant g ( x ) = ? wix ; twd + 1 i = 1 * ny Tw + 1 or - 1
Response Summing device Threshold element x : Pattern wd + 1 + 1 ...
Sivu 90
We apply this rule to each element of Sø to generate the sequence Sz . The final
step of the proof is to form a sequence Sy of RD - dimensional weight vectors
from the reduced weight - vector sequences , SW , . . . , SÊ R . Let Vi be the kth ...
We apply this rule to each element of Sø to generate the sequence Sz . The final
step of the proof is to form a sequence Sy of RD - dimensional weight vectors
from the reduced weight - vector sequences , SW , . . . , SÊ R . Let Vi be the kth ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Sisältö
Preface vii | 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 belonging to category called changes Chapter cluster committee components consider consists contains correction corresponding covariance decision surfaces define denote density depends derivation described Development discriminant functions discussed distance distribution element equal error-correction estimates example exists expression FIGURE fixed given implemented important initial layered machine linear dichotomies linear machine linearly separable matrix measurements negative networks normal Note optimum origin parameters partition pattern classifier pattern hyperplane pattern space pattern vector piecewise linear plane points positive presented probability problem proof properties proved PWL machine quadric reduced regions respect response rule sample mean selection separable shown side solution space Stanford step Suppose theorem theory threshold training methods training procedure training sequence training subsets transformation values weight vectors zero