DeepLearning4J Extension - (Early Release, Needs Feedback)

JEdwardJEdward RapidMiner Certified Analyst, RapidMiner Certified Expert, MemberPosts:578Unicorn
edited November 2018 inHelp
Hi guys,

We have created an extension to integrate DeepLearning4J into RapidMiner!
什么we need, before release on marketplace, is a small army of bug finders & volunteers to become fixers of the extension.

Download here & help us out.
https://www.rapidminerchina.com/2016/02/rapidminer-china-announces-rapidminer-deeplearning4j-integration/
(Please note, this is still underdevelopment so use in production at your own risk)
Tagged:
Thomas_Ott

Answers

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
    I've tested it and i need to say:
    Thank you for this! It is already great! (Even if i run into some null pointers..):)
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • JEdwardJEdward RapidMiner Certified Analyst, RapidMiner Certified Expert, MemberPosts:578Unicorn
    Although it needs pointed at a text file at the moment, I recommend trying out Word2Vec, it's actually pretty interesting way to look at relationships between words. The hierarchical cluster tree also provides a fun way to navigate around them too.




















    <参数键= "模式" value = " CompleteLink " / >
























    Thomas_Ott
  • NeuralMarketNeuralMarket MemberPosts:13Contributor II
    I must try this. Thanks for your hard work!
    Thomas_Ott
  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist
    Hey John,

    quick question: How can i apply the model returned by of word2vec?

    ~Martin
    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
  • JEdwardJEdward RapidMiner Certified Analyst, RapidMiner Certified Expert, MemberPosts:578Unicorn
    It turned out to be less than a quick question. ::)

    I created a process based on the rules here:http://deeplearning4j.org/word2vec(which is a really nice explanation on how it'should'work) I created a sample process which applies the similarity operators, aggregate, clustering & PCA on the result to try to demonstrate it.
    Trust me, it was a thing of beauty using the aggregate, differencing, append & similarity operators in various combinations.

    Unfortunately, it doesn't work with as I expected on the complete works of Shakespeare so we're debugging the operator to see if something needs to be tweaked internally.:D
  • kenedykenedy MemberPosts:1Contributor I
    I really like what you have shared here.
  • kaymankayman MemberPosts:662Unicorn

    Hi, this seems to be no longer available, any way to still get hold of this?

  • MartinLiebigMartinLiebig Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University ProfessorPosts:3,404RM Data Scientist

    Hi,

    it's still compilable from GitHub:https://github.com/LostSummer233/rapidminer-extension-dl4j-pack

    ~Martin

    - Sr. Director Data Solutions, Altair RapidMiner -
    Dortmund, Germany
    kayman Thomas_Ott
  • KPLKPL RapidMiner Certified Analyst, MemberPosts:9Contributor II

    It's been a while since your last post. Is RapidMiner going forward with this extension or dropping it? I'm looking for a recurrent NN plug-in for RM and this seemed to be it. Any other recommendations for RNN & RM?

Sign InorRegister置评。