Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 12
Sivu 69
In the error - correction training procedures , the training patterns are presented
to the trainable TLU one at a time for trial . The trial consists of comparing the
actual response of the TLU with the desired response dictated by the category of
the ...
In the error - correction training procedures , the training patterns are presented
to the trainable TLU one at a time for trial . The trial consists of comparing the
actual response of the TLU with the desired response dictated by the category of
the ...
Sivu 75
Suppose that a pattern Y belonging to category i is presented with the result that
some discriminant , say the jth ( j + i ) , is larger than the ith . That is , the machine
erroneously places Y in category 3 . The weight vectors used by both the ith and
...
Suppose that a pattern Y belonging to category i is presented with the result that
some discriminant , say the jth ( j + i ) , is larger than the ith . That is , the machine
erroneously places Y in category 3 . The weight vectors used by both the ith and
...
Sivu 126
visions for the birth and death of weight vectors during the adjustment procedure .
REFERENCES 1 Duda , R . O . , and R . C . Singleton : Training a Threshold
Logic Unit with Imperfectly Classified Patterns , paper presented at 1964
WESCON ...
visions for the birth and death of weight vectors during the adjustment procedure .
REFERENCES 1 Duda , R . O . , and R . C . Singleton : Training a Threshold
Logic Unit with Imperfectly Classified Patterns , paper presented at 1964
WESCON ...
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