* Add pipeline to documentation homepage. * Fix for mobile devices. * Add little pipelines to go at the top of each page. * Overhaul index page. * Overhaul README to remove redundant material. * Add installation documentation. * Update pipelines. * Allow nesting of deeper details. * Add a pipeline to the top of the load/save page. * Add prerequisites link to main pipeline. * Add better but not finished sidebar. * Add a couple new documentation pages. * Fix URLs in svg. * Incremental checkin. * Fix Youtube URLs. * Incremental checkin. * Minor fixes. * Add first pass at evaluation/deployment pages. * Minor spacing and link fixes. * Flesh out a number of additional pages and write basic compilation documentation. * Fix some minor issues, and add Docker deployment page (not totally finished yet). * Add developer documentation landing page. * Hopefully getting close to the final set of changes here. * Remove this documentation for now. * Fix a few links, and the size of the sidebar. * Fix some additional links. * Fix a bunch more links. * Fix another link that now has a better place. * Refactor test-docs.sh to handle documentation that is a standalone program. * Fix file exclusions. * Fully qualify typename. * Update name of file. * Fix syntax error. * Remove files that are not meant to be compiled. * Also skip the quickstart. * Move quickstart entry to the top. * Remove gray coloring of binding documentation. * Update name of sidebar link. * Update to working link. * Fix Wikipedia anchor.
1.3 KiB
1.3 KiB
Transformations
Once data is loaded and any necessary preprocessing and feature extraction is done, one of mlpack's transformations can be used to transform data into a new space.
Note: this section is under construction and not all functionality is documented yet.
Matrix decompositions
Decompose a matrix into two or more components.
Linear transformations
Linearly map a matrix onto a new basis, optionally performing dimensionality reduction.
Metric learning techniques
Learn a distance metric based on a data matrix.
Coding techniques
Encode data points in a matrix as a combination of points in a dictionary.
- LocalCoordinateCoding: local coordinate coding with dictionary learning
- SparseCoding: sparse coding with dictionary learning