Are you happy with your logging solution? Would you help us out by taking a 30-second survey? Click here

nupic

Numenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strictly on the neuroscience of the neocortex.

Subscribe to updates I use nupic


Statistics on nupic

Number of watchers on Github 5517
Number of open issues 441
Average time to close an issue 4 days
Main language Python
Average time to merge a PR 2 days
Open pull requests 51+
Closed pull requests 107+
Last commit over 1 year ago
Repo Created over 6 years ago
Repo Last Updated over 1 year ago
Size 149 MB
Homepage http://numenta.org/
Organization / Authornumenta
Latest Release1.0.3
Contributors69
Page Updated
Do you use nupic? Leave a review!
View open issues (441)
View nupic activity
View on github
Fresh, new opensource launches πŸš€πŸš€πŸš€
Trendy new open source projects in your inbox! View examples

Subscribe to our mailing list

Evaluating nupic for your project? Score Explanation
Commits Score (?)
Issues & PR Score (?)

NuPIC Logo NuPIC

Numenta Platform for Intelligent Computing

The Numenta Platform for Intelligent Computing (NuPIC) is a machine intelligence platform that implements the HTM learning algorithms. HTM is a detailed computational theory of the neocortex. At the core of HTM are time-based continuous learning algorithms that store and recall spatial and temporal patterns. NuPIC is suited to a variety of problems, particularly anomaly detection and prediction of streaming data sources. For more information, see numenta.org or the NuPIC Forum.

For usage guides, quick starts, and API documentation, see http://nupic.docs.numenta.org/.

This project is in Maintenance Mode

We plan to do minor releases only, and limit changes in NuPIC and NuPIC Core to:

  • Fixing critical bugs.
  • Features needed to support ongoing research.

Installing NuPIC

NuPIC binaries are available for:

  • Linux x86 64bit
  • OS X 10.9
  • OS X 10.10
  • Windows 64bit

Dependencies

The following dependencies are required to install NuPIC on all operating systems.

Additional OS X requirements:

Install

Run the following to install NuPIC:

pip install nupic

Test

# From the root of the repo:
py.test tests/unit

Having problems?

  • You may need to use the --user flag for the commands above to install in a non-system location (depends on your environment). Alternatively, you can execute the pip commands with sudo (not recommended).
  • You may need to add the --use-wheel option if you have an older pip version (wheels are now the default binary package format for pip).

For any other installation issues, please see our search our forums (post questions there). You can report bugs at https://github.com/numenta/nupic/issues.

Live Community Chat: Gitter

Installing NuPIC From Source

To install from local source code, run from the repository root:

pip install .

Use the optional -e argument for a developer install.

If you want to build the dependent nupic.bindings from source, you should build and install from nupic.core prior to installing nupic (since a PyPI release will be installed if nupic.bindings isn't yet installed).

  • Build: Build Status AppVeyor Status CircleCI
  • To cite this codebase: DOI
nupic open issues Ask a question     (View All Issues)
  • almost 3 years Unnecessary semicolons in multiple files.
  • almost 3 years NuPIC Walkthrough notebook's "int" dtype doesn't work on some platforms
  • almost 3 years Encoders' output is incompatible with the C++ SpatialPooler
  • almost 3 years Get NuPIC running in Sage
  • almost 3 years Make `anomaly_likelihood.py` compliant to Python3
  • almost 3 years SpatialPooler: inhibitColumnsGlobal() does unneeded reverse sort on returned list
  • almost 3 years Install NuPIC using Docker
  • almost 3 years with out-of-bounds index 29, but container only holds 29 elements.
  • almost 3 years Proposal: SP potentialRadius should default to -1
  • almost 3 years Better document how to create anomaly models in the OPF from swarm results
  • almost 3 years SpatialPooler: Needs Additional Documentation re: PotentialRadius
  • almost 3 years The TM compatibility test fails with some seeds
  • almost 3 years Stop requiring $USER to be set
  • almost 3 years Support better extensibility of Connections
  • almost 3 years Bug in recursive AnomalyLikelihood calculation of left tail probabilities
  • almost 3 years some debugs are exsists in one_gym example.
  • almost 3 years Docker: Install nupic.core from pypi, not build locally
  • almost 3 years Delta encoder shouldn't use the Adaptive Scalar Encoder
  • almost 3 years Error in TM Unit Test, hearkens on another potential issue
  • about 3 years Connections: createSynapse() has non-optimal / unneeded if test
  • about 3 years Connections: createSegment() method has missing break for short circuiting
  • about 3 years Add a "checkInputs" parameter to TemporalMemory
  • about 3 years Bug in adding synapses in temporal_memory
  • about 3 years TM has missing doc strings and possible param redundancy
  • about 3 years Incorrect terminology in spatial_pooler.py
  • about 3 years Error running hierarchy_network_demo.py
  • about 3 years Another regression test failure on NAB tests
  • about 3 years TemporalMemory.growSynapses() Method Needs Explicit Test
  • about 3 years Is this expected test result after running py.test tests/unit ?
  • about 3 years Test installation on Ubuntu 16
nupic open pull requests (View All Pulls)
  • Make it easier to subclass RecordSensor.py
  • Updates nupic.core to latest build SHA.
  • Add capnproto serialization to TPRegion
  • SpatialPoolerEncoder
  • Serialization migration utility
  • Fix TP non "fixed-sized" mode
  • Anomaly metric
  • Use nupic.core encoders from nupic via the Network API: Take 2
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Get the C++ TM running in the integration tests
  • Implement SDRClassifierRegion in NuPIC
  • Reserved slots in CategoryEncoder. Fixes #3094
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Optimal default params
  • Example of pylint on a PR.
  • Sp profile review
  • Fixed #3165 by changing the verbosity variable proto name
  • fixes connection tests and prints config file used in test_db.py
  • Updates nupic.core to latest build SHA.
  • Added examples illustrating properties of Temporal Memory
  • Calculate tail probabilities explicitly in anomaly_likelihood
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Updates nupic.core to latest build SHA.
  • Fix bad column ref. Cleanup whitespace / typos.
  • Initial changes, removing .nupic_modules and relying on regular Pytho…
  • Add nyc taxi example for anomaly detection
  • Remove the notion of "destroyed" Segments / Synapses
  • Add a lot more scenarios to the TM perf benchmark
  • SpatialPooler: Stop exempting overlap=0 from stimulusThreshold
  • DEVOPS-184 Create nupic build plan with a single portable wheel build and multi-platform tests
  • Another PR build test
  • Fix Anomaly Likelihood calc of tail probabilities
  • Makes `anomaly_likelihood.py` compliant to Python3
  • update simple hotgym example in NuPIC
  • Added manual step of github release creation to docs.
  • [RES-411] Implement New SP Boosting Rules in NuPIC
  • updated __init__.py to include missing encoders
  • Use better parameters in the TM performance benchmark
  • Move segment/synapse cleanup out of Connections (Python)
  • Stop calling the backtracking_tm tests "tm tests"
  • Removed topDownCompute fn from backtracking tm
  • NUP-2487: Update category prediction example
  • Fixing nyc_taxi.csv
  • Fix some imports in the ipython notebook example
nupic questions on Stackoverflow (View All Questions)
  • NuPIC Network Predict Zeros on Simple Example
  • Python Abort trap: 6 using nupic
  • How to correctly interpret NuPIC output vol.2
  • How to correctly interpret NuPIC output
  • How to know if NuPIC is predicting or repeating?
  • Nupic Installation Ubuntu 13.04
  • Must provide path to nupic core release. export NUPIC_CORE_RELEASE=<path>
  • iPython Notebook server in 'nupic' virtual box not Accessible from OS X 10.10.3
  • Are there any NuPIC precompiled images available?
  • Failing to generate scalar predictions from NuPIC CLA model
  • NuPIC on MNIST Dataset
  • NuPIC OPF Runtime error getOutputData unknown output categoriesOut
  • Is there multi-dimensional spatial pooler for NUPIC?
  • NuPIC one_hot_gym tutorial swarm attribute error
  • NuPIC .ova image installation - for Mac OS X (10.9)?
  • Nupic : RegionTest fails, pynode cannot be found
nupic list of languages used
nupic latest release notes
1.0.3 1.0.3

Release 1.0.3.

  • Updated incorrect name for anomaly likelihood region. (#3770)
1.0.2 1.0.2

Release 1.0.2

  • Fixed BacktrackingTM serialization error (#3765)
1.0.1 1.0.1
  • Fixed a bug in record sensor that prevented the usage of CoordinateEncoder. (#3754)
Other projects in Python