Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 11
Sivu 98
3 But consider the committee " of weight vectors W1 , W2 , and W , in Fig . 6 : 3 . With respect to these weight vectors , we have the inequalities 1 2 3 W , • Y > 0 W2 : Y , < 0 W :: Yi > 0 WY , > 0 W2 · Y2 > 0 W.Y , < 0 1 W.Y , > 0 W2 ...
3 But consider the committee " of weight vectors W1 , W2 , and W , in Fig . 6 : 3 . With respect to these weight vectors , we have the inequalities 1 2 3 W , • Y > 0 W2 : Y , < 0 W :: Yi > 0 WY , > 0 W2 · Y2 > 0 W.Y , < 0 1 W.Y , > 0 W2 ...
Sivu 99
Therefore , our discussion will concentrate on the " simple - majority ' committee machine with a fixed vote - taking TLU . , Response : X : * a d Vote - taking TLU ( second layer ) Pattern r d + 1 = +1 P committee TLUS ( first layer ) ...
Therefore , our discussion will concentrate on the " simple - majority ' committee machine with a fixed vote - taking TLU . , Response : X : * a d Vote - taking TLU ( second layer ) Pattern r d + 1 = +1 P committee TLUS ( first layer ) ...
Sivu 100
Since N. cannot be even it follows that exactly ( P – Nx ) / 2 of the P Nk / committee TLUs have negative responses . If the responses of at least 42 ( Nx ] + 1 ) of these negatively responding TLUs were changed from -1 to +1 , then the ...
Since N. cannot be even it follows that exactly ( P – Nx ) / 2 of the P Nk / committee TLUs have negative responses . If the responses of at least 42 ( Nx ] + 1 ) of these negatively responding TLUs were changed from -1 to +1 , then the ...
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 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 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
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 |