Introduction to AI

Module 8: neural networks and deep learning


  • Topics:
    • Overview of neural networks
    • Brief overview of deep learning methods
    • Note, there is a whole class on this topic at OU so this module is necessarily brief: only one week whereas the other class is all 15 weeks!  This is just intended to get you familiar with the topics and, if you are interested, you can take the other class.
  • Length: This module will take one week to complete
  • Assigned chapters: Chapter 21
    • Optional reading: There is a fabulous free book online introducing neural networks and deep learning.  If you want to go into much more depth, I highly recommend Neural Networks and Deep Learning
  • Project: No new projects assigned in this module as you are working on Project 5

Neural networks and deep learning

Neural networks, and specifically deep learning, seem to have taken over the AI/ML world, at least if you focus only on what you see in the news.  As you have learned in this class, there is a lot to AI!  In this module, we will just scratch the surface of what a neural network is and how neural networks relate to deep learning.  

Neural networks, specifically the fully-connected feed forward networks that we will study first in this module, have been around for multiple decades.  The reason that you hear more about them recently has to do with the success of the deep learning and convolutional networks (CNNs).  In the past 5 years or so, CNNs have shown up in the news given their great success at identifying a wide variety of images.  They have found their way into a wide variety of applications, including your smart phone in ways you probably don’t even notice! 

The ubiquitous application of ML for image recognition has also sparked a recognition that it can be misused as well.  While we will not discuss that in this module, we will in the AI & ethics module coming up in a few weeks!   

Convolutional Neural Networks

graphic showing a convolutional neural network for a bird

Graphic from “A Beginner’s Guide To Understanding Convolutional Neural Networks

Assignments for Module 8

Topic 1: neural networks

Before jumping into deep learning, we will learn about fully connected neural networks as they are an integral part of deep learning.

  • (30 min) Reading
    • Read Section 21.1 (Introduction through Simple Feedforward Networks)

Topic 2: convolutional networks and deep learning

  • (30 min) Reading
    • Read Section 21.3 (Convolutional Networks)
      • Note, the rest of the chapter is excellent but we are just doing an overview here (since you cover these in more depth in both the Machine Learning class or the Advanced Machine Learning class).  
    • Some additional reading if you are really interested in deep learning
      • Neural Networks and Deep Learning – this is a fabulous online and free textbook resource!  I highly recommend it if you want to learn more about neural networks and about deep learning as an excellent starting point.
      • Deep Learning – this is also a fabulous book with a much deeper level of math required.  If you are excited by the topic and want to learn more with all the math, this is a good book
      • Deep Learning with Python – this is a practical hands-on book about doing deep learning with python.  There are free Jupyter notebooks online from the book as well to get started.  
      • This is an article that contains a lot of links to other deep learning resources A “weird” introduction to deep learning 
  • (30 min) Videos 
    • Watch my video on an overview of deep learning and convolutional networks
    • If you want a really high-level view of deep learning, this quick YouTube video is good
    • If you really love deep learning and want to learn more, the books are listed above and you can find in-depth online courses here:
      • Coursera course on deep learning  
      • have more than 6 courses on deep learning, convolutional networks, and advanced topics
      • While this link isn’t all deep learning, a large number of the papers that he covers are deep learning related.  Although it is called two minute papers, each is about 5 minutes.  Very fun and informative! Two minute papers
  • Although I do not have an official exercise on the convolutional neural networks/deep learning part, you will want to learn about them as they will come up a lot in the AI & ethics discussion and plus they are what is in the news a lot!  

project for module 8


  • Since this module is only one week, there are no new projects assigned but you should be working on Project 5.

suggested schedule for module 8

week 1

  • Complete Topic 1 by Wednesday
  • Complete Topic 2 by Friday
  • Work on Project 5 all week