Feature Reduction for Unsupervised Learning
نویسندگان
چکیده
In this project, four unsupervised feature reduction algorithms for clustering problem were investigated and experimented upon two sets of data – handwritten digits data set and the functional magnetic resonance imaging (fMRI) resting state data set. Ratio of sum of squares (RSS), leverage score (LEV), and Laplacian score (LAP) were used to rank the influences of the features in the clustering. Similarity based method were implemented to find largest groups of features that dominate the clustering result. Clustering results were evaluated and compared using both accuracy score and average fisher score.
منابع مشابه
A Neural Network for Feature Extraction
The paper suggests a statistical framework for the parameter estimation problem associated with unsupervised learning in a neural network, leading to an exploratory projection pursuit network that performs feature extraction, or dimensionality reduction.
متن کاملUnsupervised feature selection using clustering ensembles and population based incremental learning algorithm
This paper describes a novel feature selection algorithm for unsupervised clustering, that combines the clustering ensembles method and the population based incremental learning algorithm. The main idea of the proposed unsupervised feature selection algorithm is to search for a subset of all features such that the clustering algorithm trained on this feature subset can achieve the most similar ...
متن کاملCompressive Feature Learning
This paper addresses the problem of unsupervised feature learning for text data. Our method is grounded in the principle of minimum description length and uses a dictionary-based compression scheme to extract a succinct feature set. Specifically, our method finds a set of word k-grams that minimizes the cost of reconstructing the text losslessly. We formulate document compression as a binary op...
متن کاملDimension Reduction
When data objects that are the subject of analysis using machine learning techniques are described by a large number of features (i.e. the data is high dimension) it is often beneficial to reduce the dimension of the data. Dimension reduction can be beneficial not only for reasons of computational efficiency but also because it can improve the accuracy of the analysis. The set of techniques tha...
متن کاملFeature Dimensionality Reduction by Manifold Learning in Brain-computer Interface Design
Unsupervised manifold learning for dimensionality reduction has drawn much attention in recent years. This paper applies two manifold learning methods for the first time to feature dimensionality reduction in brain-computer interface (BCI) design, and compares them with principal component analysis (PCA) and supervised PCA that is mathematically equivalent to the common spatial patterns (CSP) m...
متن کاملDimensionality Reduction Through Unsupervised Features Selection
As the storage technologies evolve, the amount of available data explodes in both dimensions: samples number and input space dimension. Therefore, one needs dimension reduction techniques to explore and to analyse his huge data sets. Many features selection approaches have been proposed for the supervised learning context, but only few techniques are available to address this issue in the unsup...
متن کامل