Learning Machines: Foundations of Trainable Pattern-classifying Systems |
Kirjan sisältä
Tulokset 1 - 3 kokonaismäärästä 27
Sivu 79
CHAPTER 5 CHAPTER TRAINING THEOREMS 5 : 1 The fundamental training
theorem In this chapter we shall formally state and prove some theorems about
the training procedures mentioned in Chapter 4 . These theorems form the core
of ...
CHAPTER 5 CHAPTER TRAINING THEOREMS 5 : 1 The fundamental training
theorem In this chapter we shall formally state and prove some theorems about
the training procedures mentioned in Chapter 4 . These theorems form the core
of ...
Sivu 88
We can now state the following theorem . Theorem 5 · 2 Let the training subsets
Y1 , Y2 , . . . , Yr be linearly separable . Let Sw , Sw , , . . , SwR be the weight -
vector sequences generated by any training sequence Sy , using the generalized
...
We can now state the following theorem . Theorem 5 · 2 Let the training subsets
Y1 , Y2 , . . . , Yr be linearly separable . Let Sw , Sw , , . . , SwR be the weight -
vector sequences generated by any training sequence Sy , using the generalized
...
Sivu 90
6 A related training theorem for the case R = 2 In Chapter 4 we discussed
another error - correction procedure , the fractional correction rule . In this rule the
correction increment at the kth step Ck is set equal to that value which will move
the ...
6 A related training theorem for the case R = 2 In Chapter 4 we discussed
another error - correction procedure , the fractional correction rule . In this rule the
correction increment at the kth step Ck is set equal to that value which will move
the ...
Mitä ihmiset sanovat - Kirjoita arvostelu
Yhtään arvostelua ei löytynyt.
Sisältö
Preface vii | 1 |
SOME NONPARAMETRIC TRAINING METHODS | 65 |
TRAINING THEOREMS | 79 |
Tekijänoikeudet | |
2 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