Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 27
Sivu 70
For one of them , called the fixed - increment rule , c is taken to be any fixed number greater than zero . When c is equal to one , for example , each weight is altered by the addition ( or subtraction ) of the corresponding pattern ...
For one of them , called the fixed - increment rule , c is taken to be any fixed number greater than zero . When c is equal to one , for example , each weight is altered by the addition ( or subtraction ) of the corresponding pattern ...
Sivu 71
In one case , c is a fixed constant so that the distance moved toward a particular pattern hyperplane is always the same . This fixed distance may or may not be sufficient to cross the pattern hyperplane and thus correct the error .
In one case , c is a fixed constant so that the distance moved toward a particular pattern hyperplane is always the same . This fixed distance may or may not be sufficient to cross the pattern hyperplane and thus correct the error .
Sivu 107
Committee machines always have a fixed hyperplane in the I1 space , and this hyper- plane is the perpendicular bisector of a major diagonal of the image - space cube . The process of training the committee machine is then a search for a ...
Committee machines always have a fixed hyperplane in the I1 space , and this hyper- plane is the perpendicular bisector of a major diagonal of the image - space cube . The process of training the committee machine is then a search for a ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Sisältö
TRAINABLE PATTERN CLASSIFIERS | 1 |
PARAMETRIC TRAINING METHODS | 43 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
Tekijänoikeudet | |
3 muita osia ei näytetty
Muita painoksia - Näytä kaikki
Yleiset termit ja lausekkeet
adjusted apply assume bank called cells changes Chapter classifier cluster column committee machine components consider consists contains correction corresponding covariance decision surfaces define denote density depends described discriminant functions discussed distance distributions elements equal error-correction estimates example exist expression FIGURE fixed given implemented initial layered machine linear machine linearly separable lines majority matrix mean measurements modes negative networks nonparametric normal Note optimum origin parameters partition pattern hyperplane pattern space pattern vector pattern-classifying piecewise linear plane points positive presented probability problem properties PWL machine quadric regions respect response rule selection separable sequence side solution space step subsidiary discriminant Suppose terns 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 |
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 |
| Alkuperäisteoksen sijainti | Wisconsinin yliopisto - Madison |
| Digitoitu | 16. huhtikuu 2008 |
| ISBN | 0070465703, 9780070465701 |
| Pituus | 137 sivua |
| Vie sitaatti | BiBTeX EndNote RefMan |