Course 806:
Introduction to Neural Networks and Deep Learning

(4 days)

 

Course Description

This is a course to demystify Neural Networks (NN) and Deep Learning (DL). By the end of the course, you will understand the specific use cases and the NN/DL models developed for these areas. It is not a programming course. A problem domain is defined, specific use cases are explored, and then you will work with classic NN/DL models learning how it works and how it can be applied within the problem domain.

The first step in understanding a NN/DL model is to develop a conceptual model. This is a description of how the model works using word, pictures, data flow diagrams, and simple graphs to understand what the model is doing and how it does it. References are given for those interested in a mathematical approach to the model. The second step is to work with the model using class and individual exercises to learn about the model’s parameters, hyper-parameters, strengths, and limitations. After understanding a classic model, current research is described including references where more can be learned. The course works through classic MLP, Convolutional, Recurrent, and Recursive networks. The models are defined using Sci-kit, Keras, or TensorFlow as appropriate. The annotated code is available for private study.

Learning Objectives

In this course, attendees will:

  • Understand the context of Neural Networks and Deep Learning
  • Know how to use 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 word with examples of each model
  • Explore the hyperparameters for each model

Prerequisites

Familiarity with running programs from the command line is helpful, but not necessary. Understanding the concept of a function is helpful, but not necessary. NOTE: The course developers, having worked through the math, strongly believe using the models do not require understanding of the math used to implement the model.

Who Should Attend

Anyone who wants to understand Neural Network and Deep Learning.


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 Is Artificial Intelligence?
  • What Can Be Learned from Deep Learning (DL)?
  • Deep DL vs. AI

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
  • Hands-On: Learning About TensorFlow

Unit 4: MLP Networks

  • Basics of Neural Networks
  • Standardization
  • Regularization
  • Working Example
  • Application Areas
  • Hands-On: Using an MLP

Unit 5: Convolutional Neural Networks (CNN)

  • Understanding CNNs
  • Comparison to MLP
  • Using Multiple Filters
  • Working Example
  • Application Areas
  • Hands-On: Using a CNN

Unit 6: Recurrent Neural Networks (RNN)

  • Understanding RNN
  • Comparison to MLP
  • LSTM
  • Working Example
  • Application Areas
  • Hands-On: Using an LSTM Model

Unit 7: Recursive Neural Networks

  • Understanding Recursion
  • Understanding Recursive Neural Networks
  • Working Example
  • Application Areas
  • Hands-On: Using a Recursive Neural Network

Please Contact Your ROI Representative to Discuss Course Tailoring!