Course 806:
Machine Learning Part II: Neural Networks and Deep Learning

(4 days)


Course Description

This is a course is about Neural Networks and Deep Learning, the most advanced techniques in Machine Learning.

The course builds a Spark platform for executing the models and shows how Tensorflow can be used to solve some of the problems of building Deep Learning Systems. It then uses the hardware foundation to study MLP networks, Convolutional networks, Recurrent networks, and Recursive networks. The approach for each network is the same; first, understand how the model works. This is the conceptual model needed to understand how to use the network. (References are given for those who want to understand how math implements the models.) Second, work through a class exercise using the network built in class and an exercise to understand the hyperparameters of the model. Lastly, there is a discussion of the application areas for this model. The course uses Linux, Python, R, and several different Machine Learning Libraries.

Learning Objectives

  • Understand the context of Neural Networks and Deep Learning
  • Know how to build a neural network
  • Understand the data needs of deep learning
  • Have a working knowledge of MLP
  • Understand the Convolutional, Recurrent, Recurrent, and Recursive models
  • Work with class to implement examples of each model
  • Explore the hyperparameters for each model


High school algebra and basic geometry will ease the learning of the models. Some familiarity with Linux and Python or R will help the student learning implementation

Course Outline


Unit 1: Overview of Neural Networks and Deep Learning

  • What Is Machine Learning?
  • What Is a Neural Network?
  • What Is Deep Learning?
  • What Can Be Learned from Deep Learning (DL)?

Unit 2: Building a Neural Network

  • Requirements
  • Tools Needed
  • Overview of Steps
  • Demonstration Building a Neural Network

Unit 3: Tensorflow

  • Why Tensorflow
  • Conmputational Graph
  • Regression Example
  • TensorBoard
  • Modularity

Unit 4: MLP Networks

  • Basics of Neural Networks
  • Standardization
  • Regularization
  • Working Example
  • Application Areas

Unit 5: Convolutional Neural Networks (CNN)

  • Understanding CNNs
  • Comparison to MLP
  • Using Multiple Filters
  • Working Example
  • Application Areas

Unit 6: Recurrent Neural Networks (RNN)

  • Understanding RNN
  • Comparison to MLP
  • LSTM
  • Working Example
  • Application Areas

Unit 7: Recursive Neural Networks

  • Understanding Recursion
  • Understanding Recursive Neural Networks
  • Working Example
  • Application Areas

Please Contact Your ROI Representative to Discuss Course Tailoring!