Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 9
Sivu 80
The initial weight vector W , is arbitrary . We shall be interested here in
sequences Sw , which are recursively generated from a training sequence Sy by
the following rules : 1 . If the kth member of the training sequence Yk is correctly
classified ...
The initial weight vector W , is arbitrary . We shall be interested here in
sequences Sw , which are recursively generated from a training sequence Sy by
the following rules : 1 . If the kth member of the training sequence Yk is correctly
classified ...
Sivu 88
Foundations of Trainable Pattern-classifying Systems Nils J. Nilsson. The rule for
generating these sequences is as follows : W ( 1 ) , W2 ( 1 ) , . . . , WĘ ( 1 ) are
arbitrary initial weight vectors ; Yx belongs to one of the training subsets , say Yi .
Foundations of Trainable Pattern-classifying Systems Nils J. Nilsson. The rule for
generating these sequences is as follows : W ( 1 ) , W2 ( 1 ) , . . . , WĘ ( 1 ) are
arbitrary initial weight vectors ; Yx belongs to one of the training subsets , say Yi .
Sivu 103
This example can also be used to illustrate the necessity for beginning with initial
weight vectors of approximately the same length . Suppose that W2 ( 1 ) were
many times longer ( in the same direction ) than is shown in Fig . 6 . 5 . If it were ...
This example can also be used to illustrate the necessity for beginning with initial
weight vectors of approximately the same length . Suppose that W2 ( 1 ) were
many times longer ( in the same direction ) than is shown in Fig . 6 . 5 . If it were ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
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 Development discriminant functions discussed distance distribution element equal error-correction estimates example exists expression FIGURE fixed gi(X given implemented important initial layered machine linear dichotomies linear machine linearly separable matrix measurements 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 specific Stanford step Suppose theorem theory threshold training methods training procedure training sequence training subsets transformation values weight vectors zero
Viitteet tähän teokseen
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Rajoitettu esikatselu - 1997 |
Kirjaluettelon tiedot
| Otsikko | Learning Machines: Foundations of Trainable Pattern-classifying Systems McGraw-Hill series in systems science |
| Kirjoittaja | Nils J. Nilsson |
| Painos | kuvitettu |
| Kustantaja | McGraw-Hill, 1965 |
| ISBN | 0070465703, 9780070465701 |
| Pituus | 137 sivua |
| Vie sitaatti | BiBTeX EndNote RefMan |