Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 13
Sivu 84
Certainly k can be no larger than km , which is a solution to the equation kmM =
kwa or km = MW12 ( 5•21 ) Therefore , we have proved ( for ŵ1 = 0 ) that the fixed
- increment error - correction procedure must terminate after at most km steps if a
...
Certainly k can be no larger than km , which is a solution to the equation kmM =
kwa or km = MW12 ( 5•21 ) Therefore , we have proved ( for ŵ1 = 0 ) that the fixed
- increment error - correction procedure must terminate after at most km steps if a
...
Sivu 85
1 results from a simple geometric argument revealing that it is impossible to apply
the fixed - increment error - correction procedure and remain forever outside the
region of solution vectors . Let W be the solution region of weight vectors ...
1 results from a simple geometric argument revealing that it is impossible to apply
the fixed - increment error - correction procedure and remain forever outside the
region of solution vectors . Let W be the solution region of weight vectors ...
Sivu 89
Conversely , suppose that Z is linearly contained with an RD - dimensional vector
V . This vector can be partitioned to yield the solution weight vectors W1 , W2 , . . .
, WR . The next step in the proof is to form from the reduced training sequence ...
Conversely , suppose that Z is linearly contained with an RD - dimensional vector
V . This vector can be partitioned to yield the solution weight vectors W1 , W2 , . . .
, WR . The next step in the proof is to form from the reduced training sequence ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Sisältö
Preface vii | 1 |
PARAMETRIC TRAINING METHODS | 43 |
TRAINING THEOREMS | 79 |
Tekijänoikeudet | |
1 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
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 |
| Pituus | 137 sivua |
| Vie sitaatti | BiBTeX EndNote RefMan |