/DeepLearning

Deep Learning (Python, C, C++, Java, Scala, Go)

Primary LanguageJavaMIT LicenseMIT

Deep Learning (Python, C, C++, Java, Scala, Go)

Classes :

  • DBN: Deep Belief Nets

  • CDBN: Deep Belief Nets w/ continuous-valued inputs

  • RBM: Restricted Boltzmann Machine

  • CRBM: Restricted Boltzmann Machine w/ continuous-valued inputs

  • dA: Denoising Autoencoders

  • SdA: Stacked Denoising Autoencoders

  • LogisticRegression: Logistic Regression

  • HiddenLayer: Hidden Layer of Neural Networks

  • MLP: Multiple Layer Perceptron

  • Dropout: Dropout MLP

  • CNN: Convolutional Neural Networks (See dev branch.)

References :

  • Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle: Greedy Layer-Wise Training of Deep Networks, Advances in Neural Information Processing Systems 19, 2007

  • P. Vincent, H. Larochelle, Y. Bengio, P.A. Manzagol: Extracting and Composing Robust Features with Denoising Autoencoders, ICML' 08, 1096-1103, 2008

  • DeepLearningTutorials https://github.com/lisa-lab/DeepLearningTutorials

  • Yusuke Sugomori: Stochastic Gradient Descent for Denoising Autoencoders, http://yusugomori.com/docs/SGD_DA.pdf

Publication :

  • More detailed Java implementations are introduced in my book, Java Deep Learning Essentials.

    The book is available from Packt Publishing or Amazon.

Bug reports / contributions / donations are deeply welcome.

Bitcoin wallet address: 34kZarc2uBU6BMCouUp2iudvZtbmZMPqrA