An applied study on recursive estimation methods, neural networks and forecasting

Article Abstract:

Three methods for univariate time series forecasting are evaluated including the Kalman filter procedure, the Recursive Least Squares (RLS) algorithm and variants, and the Levenberg-Marquardt algorithm. The DTR-IAR(1) model was approximated efficiently by the Kalman filter, which were congruent with results from RBF models applied with the RLS algorithm. Results from using the Levenberg-Marquardt method were comparatively satisfactory but exhibited efficiency and convergence problems.

Research and Development in the Physical, Engineering, and Life Sciences, Mathematics, Stochastic processes, Recursion theory

---

Global optimization for artificial neural networks: a tabu search application

Article Abstract:

Tabu search (TS) proved to be an possible alternative to the problematic backpropagation approach used for neural network optimization. Results from the Monte Carlo study reveal that TS generated solutions that were far more superior than the backpropagation method. Moreover, fewer function evaluations are required to find the optimal values.

Operations Research, Methods, Mathematical optimization, Optimization theory

---

Utilization of artifical neural networks and the TD-learning method for constructing intelligent decision support systems

Article Abstract:

The development of intelligent support systems is analyzed in detail, with a focus on the usage of TD-learning and artifical neural networks.

Management Theory & Techniques, Management, Decision support systems

Similar abstracts:

• Abstracts: An approximately global optimization method for assortment problems. Dynamic programming using the Fritz-John conditions
• Abstracts: What postmodernism means to marketing managers. A twin-track networking approach to project marketing. To bid or not to bid: screening the Whorcop Project
• Abstracts: A multiobjective optimization approach to thermal generating units maintenance scheduling. A new LP-based lower bound for the cumulative scheduling problem
• Abstracts: An overview of the design and analysis of simulation experiments for sensitivity analysis. A methodology for fitting and validating metamodels in simulation
• Abstracts: A note on Kirkwood's algebraic method for decision problems. Valuation network representation and solution of asymmetric decision problems

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.