Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 18
Sivu 72
By convergent we mean that when the pattern training subsets are linearly separable , the sequence of TLU weight vectors produced by the training procedure converges toward a solution weight vector . The fixed - increment and absolute ...
By convergent we mean that when the pattern training subsets are linearly separable , the sequence of TLU weight vectors produced by the training procedure converges toward a solution weight vector . The fixed - increment and absolute ...
Sivu 84
Certainly k can be no larger than km , which is a solution to the equation km ? a2 kmM W12 or 2 km MW | 2 a2 ( 5.21 ) 1 Therefore , we have proved ( for W. 0 ) that the fixed - increment error - correction procedure must terminate after ...
Certainly k can be no larger than km , which is a solution to the equation km ? a2 kmM W12 or 2 km MW | 2 a2 ( 5.21 ) 1 Therefore , we have proved ( for W. 0 ) that the fixed - increment error - correction procedure must terminate after ...
Sivu 85
5.4 Proof 2 The following proof of Theorem 5.1 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 ...
5.4 Proof 2 The following proof of Theorem 5.1 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 ...
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 classifier cluster committee components consider consists contains correction corresponding decision surfaces define denote density depends derivation described discriminant functions discussed distance distribution element equal error-correction estimates example exists expression FIGURE fixed gi(X given illustrated implemented important initial known layered machine linear dichotomies linear machine linearly separable negative 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 selected separable shown side space specific Stanford step Suppose theorem theory threshold training methods training patterns 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 |