benjamn / nupic

Numenta Platform for Intelligent Computing: a brain-inspired machine intelligence platform, and biologically accurate neural network based on cortical learning algorithms.

NuPIC

Numenta Platform for Intelligent Computing

• Build:
• Unit Test Coverage:
• Regression Tests:

NuPIC is a library that provides the building blocks for online prediction and anomaly detection systems. The library contains the Cortical Learning Algorithm (CLA), but also the [Online Prediction Framework (OPF)] (https://github.com/numenta/nupic/wiki/Online-Prediction-Framework) that allows clients to build prediction systems out of encoders, models, and metrics.

For more information, see numenta.org or the NuPIC wiki.

Installation

For all installation options, see the Installing and Building NuPIC wiki page.

Currently supported platforms:

• Linux (32/64bit)
• Mac OSX
• Raspberry Pi (ARMv6)
• Chromebook (Ubuntu ARM, Crouton) (ARMv7)
• VM images

Dependencies:

• Python (2.6-2.7) (with development headers)
• GCC (4.6-4.8), or Clang
• Make or any IDE supported by CMake (Visual Studio, Eclipse, XCode, KDevelop, etc)

The dependencies are included in platform-specific repositories for convenience. Installing from these repositories is not required if the dependencies defined above have been manually installed or already exist on your system.

• nupic-linux64 for 64-bit Linux systems
• nupic-darwin64 for 64-bit OS X systems

Complete set of python requirements are documented in requirements.txt, compatible with pip:

Installing Python Dependencies

pip install -r external/common/requirements.txt

Note: If using pip 1.5 or later:

pip install --allow-all-external --allow-unverified PIL --allow-unverified psutil -r external/common/requirements.txt

Note: If you get a "permission denied" error when using pip, you may add the --user flag to install to a location in your home directory, which should resolve any permissions issues. Doing this, you may need to add this location to your PATH and PYTHONPATH. Alternatively, you can run pip with sudo.

Installing NuPIC

Move into the NuPIC installation directory and run:

python setup.py install

Note: If you get a "permission denied" error when using this, you may add the --user flag to install to a location in your home directory, which should resolve any permissions issues. Doing this, you may need to add this location to your PATH and PYTHONPATH. Alternatively, you can run this with sudo.

Once it is installed, you can import NuPIC library to your python script using:

import nupic

For examples, tutorials, and screencasts about using NuPIC, see the Using NuPIC wiki page.

Developer instructions

If you want develop, debug, or simply test NuPIC, clone it and follow the instructions:

Using command line

This assumes the NUPIC environment variable is set to the directory where the NuPIC source code exists.

cd $NUPIC
python setup.py build
python setup.py develop

To run the tests:

cd $NUPIC/build/scripts
# all C++ unit tests
make cpp_unit_tests
# C++ HTM Network API tests
make tests_cpphtm
# Python HTM Network API tests
make tests_pyhtm
# Python OPF unit tests
make python_unit_tests
# Python OPF integration tests
make python_integration_tests
# Python OPF swarming tests (requires mysql)
make python_swarming_tests
# Run all tests!
make tests_all

Using an IDE

See our Development Tips wiki page for details.

To run the tests:

• Run any test project from your IDE (check output panel to see the results).

For more tips, please see Development-Tips