On the geometric convergence of neural approximations

IEEE Transactions on Neural Networks

Volumn 13, Issue 2, 2002, Pages 274-282

  Lavretsky, Eugene ^a  

^a BOEING COMPANY   (United States)

Author keywords

Feedforward neural networks; Greedy approximation; Rate of approximation; Universal approximation

Indexed keywords

APPROXIMATION THEORY; CONVERGENCE OF NUMERICAL METHODS; FUNCTIONS; ITERATIVE METHODS; THEOREM PROVING;

GEOMETRIC CONVERGENCE;

FEEDFORWARD NEURAL NETWORKS;

EID: 0036505609     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.991414     Document Type: Article

References (13)

1. Approximation by superpositions of a sigmoidal function
2. Universal approximation bounds for superpositions of a sigmoidal function
3. Kolmogorov's mapping neural network existence theorem, in international joint conference in neural networks
4. Universal approximation using feedforward neural networks: A survey of some existing methods and some new results
5. A simple lemma on greedy approximations in Hilbert space and convergence rates for projection pursuit regression and neural network training
6. Representations and rates of approximations of real-valued Boolean functions by neural networks
7. Parallel networks that learn to pronounce English text
8. Finite mapping by neural networks and troth functions
9. Dimension independent bounds on the degree of approximation by neural networks
10. On the structure of continuos functions of several variables
11. A numerical implementation of Kolmogorov's superpositions
12. A numerical implementation of Kolmogorov's superpositions II