This repository hosts course materials used for a 13-week course "CIS6930 Topics in Computing for Data Science" as part of Graduate Program in Applied Data Science at New College of Florida.
This course requires the student to have basic knowledge in Machine Learning and programming skills in Python. For those who are new to Machine Learning and/or Python programming, refer to this repository, which hosts the course materials for a 3-day seminar on Machine Learning and NLP.
This course covers a line of Deep Learning techniques that have been applied to a variety of computer science problems, especially in Computer Vision and Natural Language Processing. The course will start from Deep Learning fundamentals such as basic model architecture and optimization techniques before moving onto more sophisticated techniques. This course covers commonly used techniques for Computer Vision such as Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), and for Natural Language Processing such as Recurrent Neural Networks (RNNs) and Transformer. The aim of this course is to teach both theory and practice while the students are proactively learning to apply the techniques to problems through running their own research projects.
The course also provides self-contained hands-on exercise materials that run on Google Colab, which offer quick introduction to popular "must-know" Python libraries such as Pandas, PyTorch, spaCy, Transformers, and PyTorch Lightning.
- Week 1 (9/9): Deep Learning Basics
- (Part 1) [Slides]
- (Part 2) [Slides] [Exercise & Assignment 1]
- Week 2 (9/14): AutoEncoder [Slides]
- Week 3 (9/16): Convolutional Neural Networks [Slides]
- Week 4 (9/21): Generative Adversarial Networks [Slides]
[Exercise]
- Week 5 (9/21): Word Embeddings [Slides]
[Exercise]
- Week 6-1 (9/28): Recurrent Neural Networks (1) [Slides]
- Week 6-2 (9/30): Recurrent Neural Networks (2) [Slides]
- Week 7 (10/5): Review & Mid-term [Slides]
- Week 8-1 (10/19): Transformers (1) [Slides]
- Week 8-2 (10/21): Transformers (2) [Slides]
- Week 9-1 (10/26): Pre-trained Language Models (1) [Slides]
[Exercise]
- Week 9-2 (10/28): Pre-trained Langauge Models (2) [Slides]
[Assignment 4]
- Week 10 (11/9): More Pre-trained Language Models [Slides]
[Exercise]
- Week 11 (11/16): More Deep Learning Topics (1) [Slides]
[Exercise]
- Week 12 (11/18): More Deep Learning Topics (2) [Slides]
[Exercise]
- Week 13-1 (11/23): Final Project Presentations (1)
- Week 13-2 (11/30): Final Project Presentations (2) & Final Remarks [Slides]
Here is a list of students' term projects that are publicly available at GitHub. They are all great work!