Wavelet Packet Multi-layer Perceptron for Chaotic Time Series Prediction: Effects of Weight Initialization
نویسندگان
چکیده
We train the wavelet packet multi-layer perceptron neural network (WP-MLP) by backpropagation for time series prediction. Weights in the backpropagation algorithm are usually initialized with small random values. If the random initial weights happen to be far from a good solution or they are near a poor local optimum, training may take a long time or get trap in the local optimum. Proper weights initialization will place the weights close to a good solution with reduced training time and increased the possibility of reaching a good solution. In this paper, we investigate the effect of weight initialization on WP-MLP using two clustering algorithms. We test the initialization methods on WP-MLP with the sunspots and Mackey-Glass benchmark time series. We show that with proper weight initialization, better prediction performance can be attained.
منابع مشابه
A Pmlp Based Method for Chaotic Time Series Prediction
This paper proposes a new method for prediction of chaotic time series based on Parallel Multi-Layer Perceptron (PMLP) net and dynamics reconstruction technique. The PMLP contains a number of multi-layer perceptron (MLP) subnets connected in parallel. Each MLP subnet predicts the future data independently with a different embedding dimension. The PMLP determines the final predicted result accor...
متن کاملChaotic Time Series Prediction Using Data Fusion
One of the main problems in chaotic time series prediction is that the underlying nonlinear dynamics is usually unknown. Using a nonlinear predictor to predict a chaotic time series usually puts a limit on the accuracy since the nonlinear predictor is basically an approximation of the unknown nonlinear mapping. In this paper, we propose using fusion of predictors as a method to improve the perf...
متن کاملTime series forecasting using a deep belief network with restricted Boltzmann machines
Multi-layer perceptron (MLP) and other artificial neural networks (ANNs) have been widely applied to time series forecasting since 1980s. However, for some problems such as initialization and local optima existing in applications, the improvement of ANNs is, and still will be the most interesting study for not only time series forecasting but also other intelligent computing fields. In this stu...
متن کاملPredicting Time Series with Wavelet Packet Neural Networks
Inspired by both the multilayer perceptron (MLP) and wavelet decomposition, Zhang and Benveniste proposed the wavelet MLP (W-MLP), which has been usedfor time series prediction. The wavelet packet MLP (WP-MLP) is an MLP with the wavelet packet as a feature extraction method to obtain time-frequency information. The WPMLP has been successfully applied to biomedical, image and speech classificati...
متن کاملVehicle's velocity time series prediction using neural network
This paper presents the prediction of vehicle's velocity time series using neural networks. For this purpose, driving data is firstly collected in real world traffic conditions in the city of Tehran using advance vehicle location devices installed on private cars. A multi-layer perceptron network is then designed for driving time series forecasting. In addition, the results of this study are co...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001