Soletta Machine Learning Quickstart

In this document you'll be guided through all steps needed to have Soletta™ Project's Machine Learning up and running.

If you're interested on run SML on Intel® Edison or Intel® Galileo Gen 2, please follow these instructions instead, since they differ a bit.

Start by cloning Soletta Project Machine Learning repository:

$ git clone git@github.com:solettaproject/soletta-machine-learning.git

Install the dependencies: fuzzylite-5.0, fann-2.2.0 and soletta

fuzzylite is fuzzy logic control library written in C++:

• Web site: http://www.fuzzylite.com/
• github: https://github.com/fuzzylite/fuzzylite.git
• you may find packages for your distro as well

FANN is a neural network library.

• Web site: http://leenissen.dk/fann/wp/
• github: https://github.com/libfann/fann
• some distros like Fedora, has Fann in its rpm repository.

Soletta framework was designed for making IoT devices. Some Soletta project's data types are used by SML. Also SML provides a module for Soletta project that depends on it.

• Web site: http://solettaproject.org/
• github: https://github.com/solettaproject/soletta

CMake building system is used to build SML, so it's required to install it.

After dependencies are properly installed, it's time to build SML:

$ cd soletta-machine-learning/
$ mkdir build/
$ cd build/
$ cmake ..
$ make
$ make install