This fix also solves slow execution of the shortest path computations in Isomap. Now you have compiled versions of the MEX-files as well. However, the MEX-file for your platform might be missing. I provide a number of precompiled versions of these MEX-functions in the toolbox. This is because in some parts of the code, MEX-functions are used. When you run certain code, you might receive an error that a certain file is missing. Many of the available functions are also available through the GUI, which can be executed by running the function DRGUI. The OUT_OF_SAMPLE_EST function allows you to perform an out-of-sample extension using an estimation technique, that is generally applicable. The OUT_OF_SAMPLE function allows for out-of-sample extension for the techniques PCA, LDA, LPP, NPE, LLTSA, Kernel PCA, and autoencoders. The GENERATE_DATA function provides you with a number of artificial datasets to test the techniques. Other functions that are useful are the GENERATE_DATA function and the OUT_OF_SAMPLE and OUT_OF_SAMPLE_EST functions. Information on the intrinsic dimensionality estimators can be obtained by typing the HELP INTRINSIC_DIM. For more information on the options for dimensionality reduction, type HELP COMPUTE_MAPPING in your Matlab prompt. All functions in the toolbox can work both on data matrices as on PRTools datasets (). It will create a helix dataset, estimate the intrinsic dimensionality of the dataset, run Laplacian Eigenmaps on the dataset, and plot the results. MappedX = compute_mapping(X, 'Laplacian', no_dims, 7) įigure, scatter(mappedX(:,1), mappedX(:,2), 5, labels) title('Result of dimensionality reduction'), drawnow No_dims = round(intrinsic_dim(X, 'MLE')) ĭisp() The graphical user interface of the toolbox is accessible through the DRGUI function.īasically, you only need one function: mappedX = compute_mapping(X, technique, no_dims) In addition to these techniques, the toolbox contains functions for prewhitening of data (the function PREWHITEN), exact and estimate out-of-sample extension (the functions OUT_OF_SAMPLE and OUT_OF_SAMPLE_EST), and a function that generates toy datasets (the function GENERATE_DATA). Estimator based on geodesic minimum spanning tree ('GMST') Estimator based on packing numbers ('PackingNumbers') Estimator based on nearest neighbor evaluation ('NearNb') Estimator based on correlation dimension ('CorrDim') Eigenvalue-based estimation ('EigValue') These techniques are available through the function INTRINSIC_DIM. Autoencoders using evolutionary optimization ('AutoEncoderEA')įurthermore, the toolbox contains 6 techniques for intrinsic dimensionality estimation. Autoencoders using stack-of-RBMs pretraining ('AutoEncoderRBM') Gaussian Process Latent Variable Model ('GPLVM') Fast Maximum Variance Unfolding ('FastMVU') Landmark Maximum Variance Unfolding ('LandmarkMVU') Maximum Variance Unfolding ('MVU', implemented as an extension of LLE) Conformal Eigenmaps ('CCA', implemented as an extension of LLE) Linear Local Tangent Space Alignment ('LLTSA') Linearity Preserving Projection ('LPP') Neighborhood Preserving Embedding ('NPE') t-Distributed Stochastic Neighbor Embedding ('tSNE') Symmetric Stochastic Neighbor Embedding ('SymSNE') Generalized Discriminant Analysis ('KernelLDA') These techniques are all available through the COMPUTE_MAPPING function or trhough the GUI. This Matlab toolbox implements 32 techniques for dimensionality reduction. In order to compile all MEX-files, type cd() in your Matlab prompt, and execute the function MEXALL. Precompiled versions of these MEX-files are distributed with this release, but the compiled version for your platform might be missing. Some of the functions in the toolbox use MEX-files. Subsequently, press the Save button in order to save your changes to the Matlab search path. Click the 'Add with subfolders.' button, select the folder $MATLAB_DIR/toolbox/drtoolbox in the file dialog, and press Open. Start Matlab and select 'Set path.' from the File menu. Matlab Toolbox for Dimensionality Reduction (v0.7.1b)Īffiliation: University of California, San Diego / Delft University of TechnologyĬopy the drtoolbox/ folder into the $MATLAB_DIR/toolbox directory (where $MATLAB_DIR indicates your Matlab installation directory).
0 Comments
Leave a Reply. |