Skip to content

megaSpoon/BigDL-Tutorials

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Deep Leaning Tutorials on Apache Spark using BigDL

Step-by-step Deep Leaning Tutorials on Apache Spark using BigDL. The tutorials are inspired by Apache Spark examples, the Theano Tutorials and the Tensorflow tutorials.

  • Preface

    • prologgue
    • Organization of the tutorials
    • advices and prerequisites for learners
  • Introduction to Spark basics(topic 1-4)

    • introduction to What Spark is, current usage and application(provided by useful links from Spark official site)
    • environment setting and install instructions
    • RDD
    • DataFrame
    • SparkSAL
    • Structured Streaming
  • Supervised Learning with BigDL(topic 6-8)

    • install dependencies and set up the envrionment(imports)
    • Introduction to Supervised Learning
      • Linear Regression with BigDL(topic 6)

        • About batch training
        • Data Generation
        • Hyperperameter setup
        • model creation with Linear layer
        • Loss function
        • Optimizer
        • Execute Training
        • Prediction on training data
        • Model evaluation on random test data
      • Binary classification with logistic regression

        • similar to structure in "Linear Regression with BigDL" but we bring the introduction to "BigDL's train_summary and validation summary API" and "how to use them to visualize the learing curve" here
      • Multiclass classification with logistic regression(topic 8)

        • introduction to MNIST dataset (topic 7)
        • rest is same to the structure in "Linear Regression with BigDL"
      • Overfitting and Regularization with BigDL

        • What is overfitting with example
        • Use regulariztion to solve overfitting
        • regularization in BigDL
  • Nerual Networks with BigDL

    • Introduction to neural networks
    • install dependencies and imports
    • mechanics of weight and gradient update
      • Forward and backward(topic 5)
    • Feedforward Neural Network(topic 9)
    • RNN(topic 11)
    • Bi-RNN(topic 13)
    • LSTM(topic 12)
    • CNN(topic 10 will include "batch normalization" here)
      • batch normalization
    • Auto-encoder(topic 14)

    These neural network topics will have the same structure in "Binary classification with logistic regression"

Topics

  1. RDD
  2. DataFrame
  3. SparkSQL
  4. StructureStreaming
  5. Forward and backward
  6. Linear Regression
  7. Introduction to MNIST
  8. Logistic Regression
  9. Feedforward Neural Network
  10. Convolutional Neural Network
  11. Recurrent Neural Network
  12. LSTM
  13. Bi-directional RNN
  14. Auto-encoder

About

Step-by-step Deep Leaning Tutorials on Apache Spark using BigDL

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Jupyter Notebook 98.7%
  • Shell 1.1%
  • Python 0.2%