A Fast Model-Building Method for Time Series Using Genetic Programming
نویسندگان
چکیده
(1) Optimization of Model Parameters After the crossover composes a functional form, the model parameters are optimized by a repetition algorithm imitating back propagation of neural networks. The following two steps are performed for each individual in each generation. step-1 initialization In each generation, initial values of the parameters in an model (offspring) are inherited from the parents. step-2 repetition Each parameter is updated from the root to leaves based on the steepest descent method that is a main part of the BP algorithm, . The step-2 is repeated for all the parameters and for all the data until a given terminal condition is satisfied.
منابع مشابه
GP-Based Modeling Method for Time Series Prediction with Parameter Optimization and Node Alternation
A fast method of GP-based model building for time series prediction is proposed. The method involves two newly-devised techniques. One is regarding determination of model parameters: only functional forms are inherited from their parents with genetic programming, but model parameters are not inherited. They are optimized by back-propagation-like algorithm when a child (model) is newborn. The ot...
متن کاملA Fast and Self-Repairing Genetic Programming Designer for Logic Circuits
Usually, important parameters in the design and implementation of combinational logic circuits are the number of gates, transistors, and the levels used in the design of the circuit. In this regard, various evolutionary paradigms with different competency have recently been introduced. However, while being advantageous, evolutionary paradigms also have some limitations including: a) lack of con...
متن کاملIdentification of outliers types in multivariate time series using genetic algorithm
Multivariate time series data, often, modeled using vector autoregressive moving average (VARMA) model. But presence of outliers can violates the stationary assumption and may lead to wrong modeling, biased estimation of parameters and inaccurate prediction. Thus, detection of these points and how to deal properly with them, especially in relation to modeling and parameter estimation of VARMA m...
متن کاملFuzzy Programming for Parallel Machines Scheduling: Minimizing Weighted Tardiness/Earliness and Flow Time through Genetic Algorithm
Appropriate scheduling and sequencing of tasks on machines is one of the basic and significant problems that a shop or a factory manager encounters; this is why in recent decades extensive studies have been done on scheduling issues. One type of scheduling problems is just-in-time (JIT) scheduling and in this area, motivated by JIT manufacturing, this study investigates a mathematical model for...
متن کاملA Fast Strategy to Find Solution for Survivable Multicommodity Network
This paper proposes an immediately efficient method, based on Benders Decomposition (BD), for solving the survivable capacitated network design problem. This problem involves selecting a set of arcs for building a survivable network at a minimum cost and within a satisfied flow. The system is subject to failure and capacity restriction. To solve this problem, the BD was initially proposed with ...
متن کامل