Description:

MLPACK is the first comprehensive scalable machine learning library. Developed by the Fundamental Algorithmic and Statistical Tools laboratory (FASTlab), MLPACK and its core functions library FASTlib are the much needed filling of an existing void. Previously, researchers had to either (a) settle for poorly-scaling collections of methods implemented for academic purposes, (b) hunt down the often difficult to find and difficult to apply yet fast code writen by algorithms' developers, or (c) reimplement solutions to their specific analysis problems from scratch. With MLPACK, we offer a fourth option, in which researchers may find all the methods they need designed favoring both speed and usability.

MLPACK currently includes a wide range of the following efficient algorithms:

• $k$-nearest neighbor classifier.

• FastICA.

• Hidden Markov Models.

• Information Maximization algorithm for ICA.

• Kalman filter.

• Kernel density estimation algorithm using series expansion.

• Mixture of Gaussians using maximum likelihood and L2 error.

• Naive Bayes classifier.

• Nelder-Mead/Quasi-Newton optimizer.

• Series expansion library for Gaussian kernel in $O(p^D)$ and $O(D^p)$ expansions.

• Support Vector Machine classifier and regression.

• Sequential Minimal Optimization algorithm for SVM.

Changes to previous version:

Initial Announcement on mloss.org.

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Cygwin, Linux, Macosx

Data Formats: None

Tags: Clustering, Kernel Methods, Convex Optimization, Classifiaction, Density Estimation, Large Scale Learning, Kalman Filter, K Nearest Neighbor Classification, Algorithms, Classifiers, Nips2008, Kdtree

Archive: download here

Comments

Eileen (on February 13, 2009, 12:13:23)

having this problem when running fl-build-all /bin/sh: g++4: not found make: *** [$FASTLIBPATH/bin/i686_Linux_fast_gcc4_-DDISABLE_DISK_MATRIX/obj/mlpack_allnn_main.o] Error 127 and a whole lot of similar error Am i missing something?

fastlab (on February 14, 2009, 03:55:05)

You need to install gcc 4. Which platform are you running on?

Paul Rodriguez (on December 21, 2010, 21:38:24)

Hi, I've set up the ccmake configuration options as appropriate but now I'm having trouble with the make command described below, thanks, Paul Rodriguez Using a santos linux, on an intel 64 bit processor, when I execute "make install" I get the following error regarding pthread_atfork: -- A library with BLAS API found. -- A library with BLAS API found. -- A library with LAPACK API found. -- Configuring done -- Generating done -- Build files have been written to: /users/sdsc/prodriguez/mlpack-0.2/fastlib/build [ 2%] Built target template_types [ 5%] Built target template_types_detect [ 17%] Built target base [ 20%] Built target col [ 23%] Built target file [ 30%] Built target fx [ 33%] Built target la [ 35%] Built target data [ 35%] Built target tree [ 43%] Built target math [ 46%] Built target par [ 87%] Built target fastlib [ 89%] Built target otrav_test [ 92%] Built target col_test [ 94%] Building CXX object fastlib/data/CMakeFiles/dataset_test.dir/dataset_test.cc.o Linking CXX executable dataset_test /rmount/usr_apps/compilers/intel/Compiler/11.1/038/lib/intel64/libguide.so: undefined reference to `pthread_atfork' collect2: ld returned 1 exit status make[2]: *** [fastlib/data/dataset_test] Error 1 make[1]: *** [fastlib/data/CMakeFiles/dataset_test.dir/all] Error 2 make: *** [all] Error 2

Andreas Mueller (on March 20, 2012, 13:29:07)

Two comments: 1) I have not found a way to contact the project on the project website. Having to come to mloss and logging in to contact the developers seems a bit weird. 2) mlpack does not seems to build with armadilla in a non-standard location. After trying to feed cmake the correct pathes for a while I gave up and installed globally. In particular, setting the paths in the CMake configuration doesn't help much. Would be cool if you could fix that. Cheers, Andy

Ryan Curtin (on March 20, 2012, 20:22:49)

Hello Andy, I've clarified www.mlpack.org a bit to note that the Trac site is where bugs can be filed. As for finding Armadillo, I have not had a problem doing the following (in this instance, I've got Armadillo 2.99.1 built in /home/ryan/src/armadillo-2.99.1/) `build$ cmake -D ARMADILLO_INCLUDE_DIR=/home/ryan/src/armadillo-2.99.1/build/ -D ARMADILLO_LIBRARY=/home/ryan/src/armadillo-2.99.1/libarmadillo.so ../` Did those two variables (ARMADILLO_INCLUDE_DIR and ARMADILLO_LIBRARY) not work for you? If you're still having problems (or have other problems) feel free to file a ticket at http://trac.research.cc.gatech.edu/fastlab/

Leave a comment

You must be logged in to post comments.