This page contains the full semester schedule for lectures, labs, assignments, and project deliverables. Slides for lectures and labs will be publish one day before the class session. Students are encourage to download the slides ahead of time and follow along during lectures or labs. Assignments are highlighted in yellow and due dates are highlighted in red.
Module 1
Overview of Deep Learning and Python
This module introduces the course materials to students and gives an overview of Deep Learning, the current state of the art, and an refresher of the Python programming language.
Introduction and Logistics
Create a free personal Google account if you don't have one already using the following link: https://accounts.google.com/SignUp
Create a free GitHub account if you don't have one already using the following link: https://github.com/join
Python Programming Refresher
Module 2
Introduction to Artificial Neural Networks
This module provides an overview and introduction to the basic building blocks of neural networks.
Neural Networks
Building a Neural Network in TensorFlow
Training a Neural Network
Optimizing a Neural Network
Module 3
Building Deep Neural Works for Computer Vision
This module focuses on the building blocks of deep neural networks for computer vision. Specifically, Convolutional Neural Networks (CNNs) will be covered in depth, applications of CNNs to vision problems such as object detection, segmentation, etc. In the lab session, students will build a CNN for sign language recognition based on the dataset collected in the previous assignments.
Convolutional Neural Networks
Convolution Filters and Convolutional Neural Networks
CNN Applications
Data Augmentation for Sign Language Numbers
Examination
Mid-Term
October 24, 2023
The in-class exams will assess your understanding of the topics covered in lectures and labs thus far. Your ability to apply the deep learning knowledge to practical/real world problems will be tested.
Module 4
Advance Topics
This module covers advance topics such as generative adversarial networks, natural language processing, and transformers. Students will also receive a guest lecture from a faculty to inspire the final projects.
CNN for Sign Language Numbers
CNN and Mid-Term Performance
Project Work
Guest Lecture
Project Work
Generative Adversarial Neural Networks
Project Work
Natural Language Processing
Project Work
Final Examination
Project Work
FINAL
Final Project Submission and Presentation
The take-home will assess your understanding of the topics covered in lectures and labs thus far. Your ability to apply the deep learning knowledge to practical/real world problems will be tested.