CPU and GPU-accelerated Machine Learning Library
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.
command regress scala script Aug 9, 2018
data re org Jan 22, 2018
jni regress scala script Aug 9, 2018
lib regress scala script Aug 9, 2018
logs tweaks to logging Sep 24, 2017
sbt-pkg fixed sbt paths Oct 26, 2017
scripts regress scala script Aug 9, 2018
src regress scala script Aug 9, 2018
tutorials fixed scripting Aug 8, 2018
.classpath fixed notebook params Aug 7, 2018
.gitignore [Refactor] out the Layer Mar 17, 2018
.project added block mults to word2vech Nov 5, 2017
Copyright.txt added copyright notices Oct 22, 2012
LICENSE added license file Sep 20, 2014
README.md Update README.md Jun 21, 2017
benchmarks.txt Update benchmarks.txt Jun 25, 2014
bidmach regress scala script Aug 9, 2018
bidmach.cmd fixed bidmat.cmd Nov 21, 2014
bidmach65 various reverts/changes for easier merge Feb 15, 2017
bidmach_full fixes to startup scripts Jun 19, 2014
build.sbt updated sbt Oct 26, 2017
build_scala_2_10_sbt added both build files Mar 18, 2016
build_scala_2_11_sbt added build scripts for 2.10 and 2.11 Mar 18, 2016
getcudaversion.sh getcudaversion.sh Aug 20, 2016
getdevlibs.sh updated getdevlibs script Aug 18, 2016
getlibs.sh trying to remove libiomp5 dependence May 28, 2015
getnativepath.class fixes to pairembed Jun 10, 2016
getnativepath.java fixes to pairembed Jun 10, 2016
logo-64x64.png added jupyter bidmach kernel Aug 6, 2018
pom.xml fixed scala script Aug 9, 2018
readme_gui.md update Jun 1, 2018
sbt fixed sbt paths Oct 26, 2017
shortpath.bat added shortpath.bat Apr 10, 2014


BIDMach is a very fast machine learning library. Check the latest benchmarks

The github distribution contains source code only. You also need a jdk 8, an installation of NVIDIA CUDA 8.0 (if you want to use a GPU) and CUDNN 5 if you plan to use deep networks. For building you need maven 3.X.

After doing git clone, cd to the BIDMach directory, and build and install the jars with mvn install. You can then run bidmach with ./bidmach. More details on installing and running are available here.

The main project page is here.

Documentation is here in the wiki

New BIDMach has a discussion group on Google Groups.

BIDMach is a sister project of BIDMat, a matrix library, which is also on github

BIDData also has a project for deep reinforcement learning. BIDMach_RL contains state-of-the-art implementations of several reinforcement learning algorithms.