PAC learning algorithms for functions approximated by feedforward networks
Conference
·
OSTI ID:244610
- Oak Ridge National Lab., TN (United States). Center for Engineering Systems Advanced Research
The authors present a class of efficient algorithms for PAC learning continuous functions and regressions that are approximated by feedforward networks. The algorithms are applicable to networks with unknown weights located only in the output layer and are obtained by utilizing the potential function methods of Aizerman et al. Conditions relating the sample sizes to the error bounds are derived using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can be directly adapted to concept learning problems.
- Research Organization:
- Oak Ridge National Lab., TN (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC05-96OR22464
- OSTI ID:
- 244610
- Report Number(s):
- CONF-960797--1; ON: DE96008787
- Country of Publication:
- United States
- Language:
- English
Similar Records
Learning algorithms for feedforward networks based on finite samples
Finite-sample based learning algorithms for feedforward networks
On stochastic approximation algorithms for classes of PAC learning problems
Technical Report
·
Thu Sep 01 00:00:00 EDT 1994
·
OSTI ID:10190716
Finite-sample based learning algorithms for feedforward networks
Conference
·
Fri Mar 31 23:00:00 EST 1995
·
OSTI ID:43785
On stochastic approximation algorithms for classes of PAC learning problems
Conference
·
Mon Feb 28 23:00:00 EST 1994
·
OSTI ID:10128931