Course Overview

This course focuses on advancements to recent advancements to neural network architectures. It examines deep neural networks and their applications to the fields of artificial intelligence, natural language processing, machine learning, and computer graphics and vision.

Prerequisites

Students are required to have a prior background in artificial intelligence or machine learning, probability theory, matrix algebra, and calculus.

Outline

The follow list contains courses that I have taught within the past few years.

Week	Topic	Notes
1	Course Introduction	Complete the Tensorflow Lab
2	Deep Learning Fundamentals	Complete the PyTorch Lab
3	Deep Learning Fundamentals (cont.)
4	Convolutional Neural Networks	Complete the Image Classification Lab
5	Convolutional Neural Networks (cont.)
6	Recurrent Neural Networks	Complete the RNN Lab
7	RNNs and Natural Language Processing
8	Attention and Transformers	Attention Is All You Need
9	Attention and Transformers (cont.)
10	Generative Models
11	Generative Models (cont.)	Complete the GANS Lab
12	Reinforcement Learning
13	Reinforcement Learning (cont.)
14	Advanced Topics in Deep Learning
15	Final Project Presentations
16	Review and Final Examination

Major Course Topics

• Loss Functions
• Backpropagation
• Feed Forward Neural Networks
• Convolutional Neural Networks
• Recurrent Neural Networks
• Attention
• Transformers
• Sequence-to-Sequence Models
• Language Models
• Word Embeddings
• Autoencoders
• Generative Adversarial Neural Networks
• Graph Neural Networks

Assigned Reading

No reading material has been assigned. However, the following textbooks are optional and may supplement the material in this class:

• TBD

Final Project

All students will be required to complete a final project. Students will go above and beyond existing current knowledge to attempt a novel research project. Students will investigate new architectures to solve an existing problem, adapt some methodology from a different problem to solve an existing problem, or define and solve a new problem of interest.

Resources

The following resources are available for students to use.

• Introduction to the Linux Command Line

Lab Work

Review the course website for more information