Supervised Neural Gas and Relevance Learning in Learning Vector Quantization
نویسندگان
چکیده
Learning vector quantization (LVQ) as proposed by Kohonen is a simple and intuitive, though very successful prototype—based clustering algorithm.Generalized relevance LVQ (GRLVQ) constitutes a modification which obeys the dynamics of a gradient descent and allows an adaptive metric utilizing relevance factors for the input dimensions. As iterative algorithms with local learning rules, LVQ and modifications crucially depend on the initialization of the prototypes. They often fail for multimodal data. The combination of GRLVQ and the neural gas algorithm (NG) is capable of learning highly multimodal data, whereby it shares the benefits of gradient dynamics and neighborhood learning in NG and an adaptive metric from GRLVQ. Up to now, the method was applied only to artificial data sets. The aim of the paper is to demonstrate the power of the approach in a real world application of character recognition.
منابع مشابه
INTEGRATED ADAPTIVE FUZZY CLUSTERING (IAFC) NEURAL NETWORKS USING FUZZY LEARNING RULES
The proposed IAFC neural networks have both stability and plasticity because theyuse a control structure similar to that of the ART-1(Adaptive Resonance Theory) neural network.The unsupervised IAFC neural network is the unsupervised neural network which uses the fuzzyleaky learning rule. This fuzzy leaky learning rule controls the updating amounts by fuzzymembership values. The supervised IAFC ...
متن کاملSupervised Neural Gas for Learning Vector Quantization
In this contribution we combine approaches the generalized leraning vector quantization (GLVQ) with the neighborhood orientented learning in the neural gas network (NG). In this way we obtain a supervised version of the NG what we call supervised NG (SNG). We show that the SNG is more robust than the GLVQ because the neighborhood learning avoids numerically instabilities as it may occur for com...
متن کاملLearning Vector Quantization for Multimodal Data
Learning vector quantization (LVQ) as proposed by Kohonen is a simple and intuitive, though very successful prototype-based clustering algorithm. Generalized relevance LVQ (GRLVQ) constitutes a modification which obeys the dynamics of a gradient descent and allows an adaptive metric utilizing relevance factors for the input dimensions. As iterative algorithms with local learning rules, LVQ and ...
متن کاملAn Informational Energy Approach to Feature Selection
In this work, we focus on machine learning methods for handling data sets containing large amounts of irrelevant information. We address two key issues: the problem of selecting relevant features, and the problem of weighting (ranking) these features. We describe our Energy Supervised Relevance Neural Gas (ESRNG) algorithm, a kernel method which uses the maximization of Onicescu’s informational...
متن کاملBorder sensitive fuzzy vector quantization in semi-supervised learning
Abstract. We propose a semi-supervised fuzzy vector quantization method for the classification of incompletely labeled data. Since information contained within the structure of the data set should not be neglected, our method considers the whole data set during the learning process. In difference to known methods our approach uses neighborhood cooperativeness for stable prototype learning known...
متن کامل