Stacking Class Probabilities Obtained from View-Based Cluster Ensembles
نویسندگان
چکیده
In pattern recognition applications with high number of input features and insufficient number of samples, the curse of dimensionality can be overcome by extracting features from smaller feature subsets. The domain knowledge, for example, can be used to group some of the features together, which are also known as “views”. The features extracted from views can later be combined (i.e. stacking) to train a final classifier. In this work, we demonstrate that even very simple features such as class-distributions within clusters of each view can serve as such valuable features.
منابع مشابه
Cluster-Based Cumulative Ensembles
In this paper, we propose a cluster-based cumulative representation for cluster ensembles. Cluster labels are mapped to incrementally accumulated clusters, and a matching criterion based on maximum similarity is used. The ensemble method is investigated with bootstrap re-sampling, where the k-means algorithm is used to generate high granularity clusterings. For combining, group average hierarch...
متن کاملImpulse Noise Detection in OFDM Communication System Using Machine Learning Ensemble Algorithms
An impulse noise detection scheme employing machine learning (ML) algorithm in Orthogonal Frequency Division Multiplexing (OFDM) is investigated. Four powerful ML's multi-classifiers (ensemble) algorithms (Boosting (Bos), Bagging (Bag), Stacking (Stack) and Random Forest (RF)) were used at the receiver side of the OFDM system to detect if the received noisy signal contained impulse noise or not...
متن کاملCorrelation Functions, Cluster Functions, and Spacing Distributions for Random Matrices
The usual formulas for the correlation functions in orthogonal and symplectic matrix models express them as quaternion determinants. From this representation one can deduce formulas for spacing probabilities in terms of Fredholm determinants of matrix-valued kernels. The derivations of the various formulas are somewhat involved. In this article we present a direct approach which leads immediate...
متن کاملStacking with Multi-response Model Trees
We empirically evaluate several state-of-the-art methods for constructing ensembles of classifiers with stacking and show that they perform (at best) comparably to selecting the best classifier from the ensemble by cross validation. We then propose a new method for stacking, that uses multi-response model trees at the meta-level, and show that it outperforms existing stacking approaches, as wel...
متن کاملA Probabilistic Model Using Information Theoretic Measures for Cluster Ensembles
This paper presents a probabilistic model for combining cluster ensembles utilizing information theoretic measures. Starting from a co-association matrix which summarizes the ensemble, we extract a set of association distributions, which are modelled as discrete probability distributions of the object labels, conditional on each data object. The key objectives are, first, to model the associati...
متن کامل