search

numenta / nupic-legacy

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.
http://numenta.org/
GNU Affero General Public License v3.0
6.33k stars 1.56k forks source link

I'm looking for the implementation of WCCI paper #3286

Closed chickenbestlover closed 8 years ago

chickenbestlover commented 8 years ago

hello nupic,

I've read your WCCI IJCNN 2016 paper : A comparative study of HTM and other neural network models for online sequence learning with streaming data.

It's really interesting that HTM overwhelmed LSTM which is the state of the art algorithm learning streaming data.

And I read from the paper that full source code for the implementation is available on Github at https://github.com/numenta/nupic, which is here.

However, I cannot find the exact location of the code.

It would be very grateful if anyone let me know where the code is.

thank you

rhyolight commented 8 years ago

@chickenbestlover You're in the right place. This is the implementation. Code starts here: https://github.com/numenta/nupic/tree/master/src/nupic

I recommend you read our wiki: https://github.com/numenta/nupic/wiki

chickenbestlover commented 8 years ago

Thank you for your kind answer. But.. i dont think this is the implementation of wcci 2016 paper; the auther of the paper compared the performance of htm with that of lstm and elm. But here, only nupic source code exists. Even the dataset is absent.

      1. 오전 12:03에 "Matthew Taylor" notifications@github.com님이 작성:

@chickenbestlover https://github.com/chickenbestlover You're in the right place. This is the implementation. Code starts here: https://github.com/numenta/nupic/tree/master/src/nupic

I recommend you read our wiki: https://github.com/numenta/nupic/wiki

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/numenta/nupic/issues/3286#issuecomment-241442196, or mute the thread https://github.com/notifications/unsubscribe-auth/AJ2X1E7d5x-ADJMJKORnZzn2V69YGf5sks5qibpRgaJpZM4JpmQb .

rhyolight commented 8 years ago

Ah ok, you are looking for https://github.com/numenta/NAB

Matt Taylor OS Community Flag-Bearer Numenta

On Mon, Aug 22, 2016 at 8:19 AM, Jin-Man Park notifications@github.com wrote:

Thank you for your kind answer. But.. i dont think this is the implementation of wcci 2016 paper; the auther of the paper compared the performance of htm with that of lstm and elm. But here, only nupic source code exists. Even the dataset is absent.

      1. 오전 12:03에 "Matthew Taylor" notifications@github.com님이 작성:

@chickenbestlover https://github.com/chickenbestlover You're in the right place. This is the implementation. Code starts here: https://github.com/numenta/nupic/tree/master/src/nupic

I recommend you read our wiki: https://github.com/numenta/nupic/wiki

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/numenta/nupic/issues/3286#issuecomment-241442196, or mute the thread https://github.com/notifications/unsubscribe-auth/AJ2X1E7d5x- ADJMJKORnZzn2V69YGf5sks5qibpRgaJpZM4JpmQb .

— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub https://github.com/numenta/nupic/issues/3286#issuecomment-241447373, or mute the thread https://github.com/notifications/unsubscribe-auth/AAA8zplBhqYUXDyvuMTqaJn7h17lrFVaks5qib3xgaJpZM4JpmQb .

ywcui1990 commented 8 years ago

The implementation for the HTM sequence memory paper is here: https://github.com/numenta/nupic.research/tree/master/projects/sequence_prediction

This is where we compare HTM with other machine learning algorithms on sequence prediction tasks.

chickenbestlover commented 8 years ago

Thank you , but this is not what i've been lookinf for. I sent an email to Yuwei(the author) and he told me the exact location. It's here :

https://github.com/numenta/nupic.research/tree/master/projects/sequence_prediction

Anyway, thank you for your kindness.

Sincerely yours,

Jinman Park

      1. 오전 12:40에 "Matthew Taylor" notifications@github.com님이 작성:

Ah ok, you are looking for https://github.com/numenta/NAB

Matt Taylor OS Community Flag-Bearer Numenta

On Mon, Aug 22, 2016 at 8:19 AM, Jin-Man Park notifications@github.com wrote:

Thank you for your kind answer. But.. i dont think this is the implementation of wcci 2016 paper; the auther of the paper compared the performance of htm with that of lstm and elm. But here, only nupic source code exists. Even the dataset is absent.

      1. 오전 12:03에 "Matthew Taylor" notifications@github.com님이 작성:

@chickenbestlover https://github.com/chickenbestlover You're in the right place. This is the implementation. Code starts here: https://github.com/numenta/nupic/tree/master/src/nupic

I recommend you read our wiki: https://github.com/numenta/nupic/wiki

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/numenta/nupic/issues/3286#issuecomment-241442196, or mute the thread https://github.com/notifications/unsubscribe-auth/AJ2X1E7d5x- ADJMJKORnZzn2V69YGf5sks5qibpRgaJpZM4JpmQb .

— You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub https://github.com/numenta/nupic/issues/3286#issuecomment-241447373, or mute the thread https://github.com/notifications/unsubscribe-auth/ AAA8zplBhqYUXDyvuMTqaJn7h17lrFVaks5qib3xgaJpZM4JpmQb .

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/numenta/nupic/issues/3286#issuecomment-241454217, or mute the thread https://github.com/notifications/unsubscribe-auth/AJ2X1Nbmr6ATdeYW3yyj7MK5z9S15k2Dks5qicLhgaJpZM4JpmQb .