Course Syllabus

Neural Network

 

Content

We will understand a number of issues about Deep Neural Networks.  Our goal is to understand the mathematical underpinning of a number of tools in Deep Learning.  We hope that this will give you the foundation to understand and critically think about continued advances in this dynamic area.

List of Topics
Linear Regression Links to an external site.
Logistic Regression Links to an external site.
Elementary Logic Links to an external site.
Backpropagation Links to an external site.
Gradient Descent Links to an external site.
Feedforward Networks Links to an external site.
Testing, Validation, and Training Links to an external site.
Feature Importance Links to an external site.
Dropout Links to an external site.
Batch Normalization Links to an external site.
Convolutional Neural Networks Links to an external site.
Recurrent Neural Networks Links to an external site.
Reinforcement Learning Links to an external site.
Generative Adversarial Networks Links to an external site.

 

Assessments

 

Component Date/Frequency Percentage
Midterm 1 10/8 15%
Midterm 2 12/5 15%
Individual Theory Assignments Links to an external site. Each module (roughly) 25%
Group Coding Assignments Links to an external site. Each module (roughly) 25%
Deep Dive Project Links to an external site. End of Semester 20%

 

 

Miscellanea