Annealed competition of experts for a segmentation and classification of switching dynamics

Authors:
Klaus Pawelzik;Jens Kohlmorgen;Klaus-Robert Müller
Affiliations:
Institut für Theoretische Physik and SFB 185 Nichtlineare Dynamik, Universität Frankfurt, 60054 Frankfurt/M., Germany;GMD-FIRST (German National Research Center for Computer Science), Rudower Chaussee 5, 12489 Berlin, Germany;GMD-FIRST (German National Research Center for Computer Science), Rudower Chaussee 5, 12489 Berlin, Germany, and Department of Mathematical Engineering and Information Physics, University of Tokyo ...
Venue:
Neural Computation
Year:
1996

Citing 3
Cited 15

Statistical physics, mixtures of distributions, and the EM algorithm

Neural Computation
Adaptive mixtures of local experts

Neural Computation
Fast learning in networks of locally-tuned processing units

Neural Computation

Data Mining for Features Using Scale-Sensitive Gated Experts

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Bayesian Multiple Models Combination Method for Time Series Prediction

Journal of Intelligent and Robotic Systems
Sparse Regression Ensembles in Infinite and Finite Hypothesis Spaces

Machine Learning
On-line learning in changing environments with applications in supervised and unsupervised learning

Neural Networks - Computational models of neuromodulation
Multiple model-based reinforcement learning

Neural Computation
Analysis of Nonstationary Time Series Using Support Vector Machines

SVM '02 Proceedings of the First International Workshop on Pattern Recognition with Support Vector Machines
Learning-Data Selection Mechanism through Neural Networks Ensemble

MCS '01 Proceedings of the Second International Workshop on Multiple Classifier Systems
Learning to generate articulated behavior through the bottom-up and the top-down interaction processes

Neural Networks
MOSAIC Model for Sensorimotor Learning and Control

Neural Computation
Learning from imperfect data

Applied Soft Computing
Time-Series Segmentation Using Predictive Modular Neural Networks

Neural Computation
Dynamic support vector machines for non-stationary time series forecasting

Intelligent Data Analysis
Improved financial time series forecasting by combining Support Vector Machines with self-organizing feature map

Intelligent Data Analysis
Clustering sensor data for autonomous terrain identification using time-dependency

Autonomous Robots
Convergence analysis of a class of simplified background neural networks with two subnetworks

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a method for the unsupervised segmentation of data streams originating from different unknown sources that alternate in time. We use an architecture consisting of competing neural networks. Memory is included to resolve ambiguities of input-output relations. To obtain maximal specialization, the competition is adiabatically increased during training. Our method achieves almost perfect identification and segmentation in the case of switching chaotic dynamics where input manifolds overlap and input-output relations are ambiguous. Only a small dataset is needed for the training procedure. Applications to time series from complex systems demonstrate the potential relevance of our approach for time series analysis and short-term prediction.