An analysis of the metric structure of the weight space of feedforward networks and its application to time series modeling and prediction
نویسندگان
چکیده
We study symmetries of feedforward networks in terms of their corresponding groups. We nd that these groups naturally act on and partition weight space into disjunct domains. We derive an algorithm to generate representative weight vectors in a fundamental domain. The analysis of the metric structure of the fundamental domain leads to improved evaluation procedures of learning results, such as local error bars estimated using maximum-likelihood and bootstrap methods. It can be implemented eeciently even for large networks. We demonstrate the approach in the area of nonlinear time series modeling and prediction.
منابع مشابه
An Analysis of the Metric Structure of the WeightSpace of Feedforward Networks and its Application
We study symmetries of feedforward networks in terms of their corresponding groups. We nd that these groups naturally act on and partition weight space into disjunct domains. We derive an algorithm to generate representative weight vectors in a fundamental domain. The analysis of the metric structure of the fundamental domain leads to improved evaluation procedures of learning results, such as ...
متن کاملApplication of artificial neural networks on drought prediction in Yazd (Central Iran)
In recent decades artificial neural networks (ANNs) have shown great ability in modeling and forecasting non-linear and non-stationary time series and in most of the cases especially in prediction of phenomena have showed very good performance. This paper presents the application of artificial neural networks to predict drought in Yazd meteorological station. In this research, different archite...
متن کاملA Nonlinear Model of Economic Data Related to the German Automobile Industry
Prediction of economic variables is a basic component not only for economic models, but also for many business decisions. But it is difficult to produce accurate predictions in times of economic crises, which cause nonlinear effects in the data. Such evidence appeared in the German automobile industry as a consequence of the financial crisis in 2008/09, which influenced exchange rates and a...
متن کاملGeometric Modeling of Dubins Airplane Movement and its Metric
The time-optimal trajectory for an airplane from some starting point to some final point is studied by many authors. Here, we consider the extension of robot planer motion of Dubins model in three dimensional spaces. In this model, the system has independent bounded control over both the altitude velocity and the turning rate of airplane movement in a non-obstacle space. Here, in this paper a g...
متن کاملChaotic Analysis and Prediction of River Flows
Analyses and investigations on river flow behavior are major issues in design, operation and studies related to water engineering. Thus, recently the application of chaos theory and new techniques, such as chaos theory, has been considered in hydrology and water resources due to relevant innovations and ability. This paper compares the performance of chaos theory with Anfis model and discusses ...
متن کامل