Deep Learning Foundations

This three-part series introduces learners to the foundations of deep learning.

Check back soon for more details.

Learning Objectives

1. Provide an accurate definition of AI and its two primary sub-domains
2. Create a Jupyter notebook using the JupyterLab IDE with Python and Markdown blocks
3. Write Python code to create and then execute the resnet50 pre-trained model
4. Name the basic types of neural network and common applications for each
5. Recognize that AI algorithms are narrowly focused and often break in unexpected ways
6. Describe the basic operation of a neural network
7. Identify the components of a neural network and their relation to each other
8. Construct a single node perceptron in Python
9. Describe how gradient descent works and its mathematical underpinnings
10. Identify the various components of gradient descent and their relation to each other
11. Explain the function of key hyperparameters and their role in training
12. Be able to tweak a model’s hyperparameters to enhance its performance
13. Construct a multi-layered neural network using Keras