Self-Organizing Maps for Time Series
نویسندگان
چکیده
We review a recent extension of the self-organizing map (SOM) for temporal structures with a simple recurrent dynamics leading to sparse representations, which allows an efficient training and a combination with arbitrary lattice structures. We discuss its practical applicability and its theoretical properties. Afterwards, we put the approach into a general framework of recurrent unsupervised models. This generic formulation also covers a variety of well-known alternative approaches including the temporal Kohonen map, the recursive SOM, and SOM for structured data. Based on this formulation, mathematical properties of the models are investigated. Interestingly, the dynamic can be generalized from sequences to more general tree structures thus opening the way to unsupervised processing of general data structures.
منابع مشابه
Data Mining and Knowledge Discovery with Emergent Self-Organizing Feature Maps for Multivariate Time Series
Self-Organizing Feature Maps, when used appropriately, can exhibit emergent phenomena. SOFM with only few neurons limit this ability, therefore Emergent Feature Maps need to have thousands of neu-rons. The structures of Emergent Feature Maps can be visualized using U-Matrix Methods. U-Matrices lead to the construction of self-organzing classiiers possessing the ability to classify new datapoint...
متن کاملLong-Term Time Series Forecasting Using Self-Organizing Maps: the Double Vector Quantization Method
Kohonen self-organisation maps are a well know classification tool, commonly used in a wide variety of problems, but with limited applications in time series forecasting context. In this paper, we propose a forecasting method specifically designed for long-term trends prediction, with a double application of the Kohonen algorithm. We also consider practical issues for the use of the method.
متن کاملTime series forecasting: Obtaining long term trends with self-organizing maps
Kohonen self-organisation maps are a well know classification tool, commonly used in a wide variety of problems, but with limited applications in time series forecasting context. In this paper, we propose a forecasting method specifically designed for multi-dimensional long-term trends prediction, with a double application of the Kohonen algorithm. Practical applications of the method are also ...
متن کاملMonitoring and Modeling of Complex Processes Using Hierarchical Self-organizing Maps
HIERARCHICAL SELF-ORGANIZING MAPS Olli Simula, Esa Alhoniemi, Jaakko Hollm en, and Juha Vesanto Helsinki University of Technology Laboratory of Computer and Information Science FIN-02150 Espoo, Finland email: fOlli.Simula, Esa.Alhoniemi, Jaakko.Hollmen, Juha.Vesantog@hut. ABSTRACT In this paper, a neural network based analysis method for monitoring and modeling the dynamic behavior of complex i...
متن کاملNon-Linear Time Series Modeling with Self-Organization Feature Maps
A locally linear approach based on Kohonen self-organizing feature mapping (SOFM) is proposed for the modeling of non-linear time series. This approach exploits the neighborhood preserving property of Kohonen feature maps. The key difference is that the local model fitting is performed directly over a matched neighborhood of the constructed SOFM neural field. The initial results show that this ...
متن کاملSpherical Topology Self-Organizing Map Neuron Network for Visualization of Complex Data
Acknowledgements Firstly, thanks to my supervisor Tom Gedeon, and Dingyun Zhu for their recommendations and support on this project. Moreover, thanks to Uwe R. Zimmer for his suggestions about the technique of report writing. Finally, thanks to my family and my friends for their encouragements. Abstract The spherical SOM (SSOM) has been proposed in order to remove the " border effect " in conve...
متن کامل