GistTree.Com
Entertainment at it's peak. The news is by your side.

Gpumlib: Open-Source GPU ML Library

0



GPUMLib (GPU Machine Finding out Lybrary)

GPUMLib

Powering Machine Finding out

Download GPUMLib model 0.3.5

Please receive the suitable model

Positive aspects

Model 0.3.5 entails the following machine studying algorithms and parts:

  • Assist-Propagation (BP)
  • A whole lot of Assist-Propagation (MBP)
  • Non-Detrimental Matrix Factorization (NMF)
  • Semi-Supervised Non-Detrimental Matrix Factorization (SSNMF)
  • Self sustaining Coaching Arrangement (ATS) for organising BP and MBP networks
  • Neural Selective Input Mannequin (NSIM) for BP and MPB (NSIM enables
    neural networks to tackle lacking values without delay)
  • Restricted Boltzmann Machines (RBMs)
  • Deep Belief Networks (DBNs)
  • Make stronger Vector Machines (SVMs)
  • Self Organizing Maps (SOMs)
  • SOM surface recontruction
  • Radial Basis Feature Networks (RBF)*
  • Resource Allocating Networks with Lengthy Term Reminiscence(RAN)*

Now not engaged on this model as these count on CULA libraries (now mature). Nonetheless the provision code for these parts is soundless on hand. We hope to fix this snarl in future versions.

Citing GPUMLib

Whereas you fabricate use of GPUMLib on your work and make a selection to quote GPUMLib (thank you), we
would gain that you just’ll cite the suitable papers above, since they form the
core of GPUMLib.

The next publications describe work built-in in GPUMLib:

  • Traditional

    • Noel Lopes and Bernardete Ribeiro.
      GPUMLib: An ambiance obedient initiate-offer GPU machine studying library.

      Global Journal of Computer Knowledge Systems and
      Industrial Management Functions
      3: 355-362, 2011.
    • Noel Lopes, Bernardete Ribeiro, and Ricardo Quintas.
      GPUMLib: A brand fresh library to mix machine studying algorithms with
      graphics processing items.
      In
      IEEE 10th Global Conference on Hybrid Sparkling
      Systems (HIS 2010)
      , pages 229-232, August 2010.
  • Assist-Propagation, A whole lot of Assist-Propagation and Self sustaining Coaching Arrangement

    • Noel Lopes and Bernardete Ribeiro.
      An review of more than one feed-forward networks on GPUs.

      Global Journal of Neural Systems (IJNS)
      , 21(1): 31-47,
      2011.
    • Noel Lopes and Bernardete Ribeiro.
      Stochastic GPU-based multithread implementation of more than one
      help-propagation.
      In
      2d Global Conference on Agents and Man made
      Intelligence (ICAART 2010)
      , pages 271-276, 2010.
    • Noel Lopes and Bernardete Ribeiro.
      GPU implementation of the more than one help-propagation algorithm.
      In
      10th Global Conference on Sparkling Knowledge Engineering
      and Automated Finding out (IDEAL 2009), LNCS 5788
      , pages 449-456. Springer,
      2009.
    • Noel Lopes and Bernardete Ribeiro.
      An ambiance obedient gradient-based studying algorithm utilized to neural
      networks with selective actuation neurons.

      Neural, Parallel and Scientific Computations
      , 11: 253-272,
      2003.
    • Noel Lopes and Bernardete Ribeiro.
      Hybrid studying in a multi-neural community structure.
      In
      INNS-IEEE Global Joint Conference on Neural Networks
      (IJCNN 2001)
      , volume 4, pages 2788-2793, 2001.
  • Neural Selective Input Mannequin (NSIM)

    • Noel Lopes and Bernardete Ribeiro.
      Handling lacking values by procedure of a neural selective input model.

      Neural Community World
      , 22(4): 357-370, 2012.
    • Noel Lopes and Bernardete Ribeiro.
      A grand studying model for going by procedure of lacking values in many-core
      architectures.
      In
      10th Global Conference on Adaptive and Pure
      Computing Algorithms (ICANNGA 2011), Share II, LNCS 6594
      , pages 108-117.
      Springer Berlin Heidelberg, 2011.
    • Noel Lopes and Bernardete Ribeiro.
      A technique for going by procedure of lacking values by the use of selective
      activation neurons in a multi-topology framework.
      In
      IEEE World Congress on Computational Intelligence (WCCI
      2010)
      , 2010.
  • Deep Belief Networks and Restricted Boltzmann Machines

    • Noel Lopes and Bernardete Ribeiro.
      Towards adaptive studying with improved convergence of deep perception
      networks on graphics processing items.

      Pattern Recognition
      , 47(1): 114-127, 2014.
    • Noel Lopes, Bernardete Ribeiro, and João Gonçalves.
      Restricted Boltzmann machines and deep perception networks on
      multi-core processors.
      In
      The 2012 Global Joint Conference on Neural Networks
      (IJCNN)
      , 2012.
    • Noel Lopes and Bernardete Ribeiro.
      Bettering convergence of restricted Boltzmann machines by procedure of a
      studying adaptive step size.
      In
      Growth in Pattern Recognition, Image Analysis, Computer
      Vision, and Functions, LNCS 7441
      , pages 511-518. Springer Berlin /
      Heidelberg, 2012.
  • Semi-Supervised Non-Detrimental Matrix Factorization and Non-Detrimental Matrix Factorization

    • Noel Lopes and Bernardete Ribeiro.
      A speedily optimized semi-supervised non-detrimental matrix factorization
      algorithm.
      In
      IEEE Global Joint Conference on Neural Networks (IJCNN
      2011)
      , pages 2495-2500, 2011.
    • Noel Lopes and Bernardete Ribeiro.
      Non-detrimental matrix factorization implementation the use of graphic
      processing items.
      In
      11th Global Conference on Sparkling Knowledge Engineering
      and Automated Finding out (IDEAL 2010), LNCS 6283
      , pages 275-283. Springer,
      2010.
  • Resource Allocating Networks and Radial Basis Functions

    • Bernardete Ribeiro, Ricardo Quintas, and Noel Lopes.
      Overview of a useful resource allocating community with longer term memory
      the use of GPU.
      In
      10th Global Conference on Adaptive and Pure
      Computing Algorithms (ICANNGA 2011), Share II, LNCS 6594
      , pages 41-47.
      Springer, 2011.
  • Make stronger Vector Machines

    • João Gonçalves, Noel Lopes, and Bernardete Ribeiro.
      Multi-threaded enhance vector machines for pattern recognition.
      In
      Global Conference on Neural Knowledge Processing
      (ICONIP 2012), Share II, LNCS 7664
      , pages 616-623. Springer Berlin /
      Heidelberg, 2012.
  • Self-Organizing Maps and SOM surface reconstruction

    • Wai Pai Lee, Shafaatunnur Hasan, Siti Mariyam Shamsuddin, Noel Lopes.
      GPUMLib: Deep Finding out SOM Library for Ground Reconstruction,
      Global Journal of Advances in Comfy Computing and Its Functions, 9(2), pages 1-16, 2017.
    • Shafaatunnur Hasan, Siti Mariyam Shamsuddin, and Noel Lopes.
      GPU Computing and Functions,
      chapter Comfy Computing Methods for Immense Knowledge Problems, pages 235–247.
      Springer Singapore, 2014.
    • Shafaatunnur Hasan, Siti Mariyam Shamsuddin, and Noel Lopes.
      Machine studying massive recordsdata framework and analytics for massive recordsdata complications.
      Global Journal of Comfy Computing and its Application, 6(2), 2014.
    • Shafaatunnur Hasan, Siti Mariyam Shamsuddin, and Noel Lopes.
      Comfy computing systems for massive recordsdata complications.
      In 2013 Symposium on GPU Computing and Functions, 2013.

Diversified connected articles:

  • Bernardete Ribeiro and Noel Lopes.
    Low studying classifier with deep ideas.
    In
    Growth in Pattern Recognition, Image Analysis, Computer
    Vision, and Functions, LNCS 8258
    pages 182-189. Springer Berlin /
    Heidelberg, 2013.
  • Shafaatunnur Hasan, Siti~Mariyam Shamsuddin, and Noel Lopes.
    Comfy computing systems for massive recordsdata complications.
    In 2013 Symposium on GPU Computing and Functions, 2013.
  • Noel Lopes and Bernardete Ribeiro.
    Towards a hybrid NMF-based neural come for face recognition on
    GPUs.

    Global Journal of Knowledge Mining, Modelling and Management
    (IJDMMM)
    , 4(2): 138-155, 2012.
  • Bernardete Ribeiro and Noel Lopes.
    Deep perception networks for monetary prediction.
    In
    Global Conference on Neural Knowledge Processing
    (ICONIP 2011), Share III, LNCS 7064
    , pages 766-773. Springer, 2011.
  • Bernardete Ribeiro, Noel Lopes, and Catarina Silva.
    High-performance economic demolish prediction model the use of graphics
    processing items.
    In
    IEEE World Congress on Computational Intelligence (WCCI
    2010)
    , 2010.
  • Noel Lopes and Bernardete Ribeiro.
    A hybrid face recognition come the use of GPUMLib.
    In
    15th Iberoamerican Congress on Pattern Recognition (CIARP
    2010), LNCS 6419
    , pages 96-103. Springer, 2010.
  • Noel Lopes and Bernardete Ribeiro.
    MBPGPU: A supervised pattern classifier for graphical processing
    items.
    In
    15th model of the Portuguese Conference on Pattern
    Recognition (RECPAD 2009)
    , 2009.
  • Noel Lopes and Bernardete Ribeiro.
    Fleet pattern classification of ventricular arrhythmias the use of graphics
    processing items.
    In
    14th Iberoamerican Congress on Pattern Recognition (CIARP
    2009), LNCS 5856
    , pages 603-610. Springer, 2009.

Builders

Noel Lopes1,2


Bernardete Ribeiro1 (Guide)


Ricardo Quintas1


João Gonçalves1


Shafaatunnur Hasan3


Siti Mariyam Shamsuddin3


Wai Pai Lee3

1CISUC – Heart for Informatics and Systems of College of Coimbra,
Portugal

2IPG – Polytechnic of Guarda, Portugal

3UTM Immense Knowledge Centre, Skudai, Johor, Malaysia

Read More

Leave A Reply

Your email address will not be published.