ECE 57000 - Artificial Intelligence
Note:
This course will provide a graduate-level introduction to artificial intelligence (AI) with a primary focus on unsupervised learning and probabilistic models. Topics will include clustering, mixture models, density estimation, representation learning, and deep generative models. The lecture content will focus on key concepts and intuitions. The course project will enable students to dive deeper into a topic of their choice. This class is oriented towards first-year graduate students. The course will expect knowledge of linear algebra, probability distributions, random variables, and Python programming. There will be multiple programming assignments throughout the semester. The assignments are meant to reinforce the content and provide hands-on experience with the common tools of AI/ML. The course project will require reading several recent AI/ML research papers and reimplementing one of these papers.
Course Details
Lecture Hours: 3 Credits: 3
Areas of Specialization:
- Computer Engineering
Counts as:
- EE Elective
- CMPE Selective
Normally Offered:
Each Fall, Spring
Campus/Online:
On-campus and online
Requisites:
ECE 30200 and ECE 36800
Requisites by Topic:
Probabilistic methods, data structures; linear algebra; Python programming
Catalog Description:
This course will provide a graduate-level introduction to artificial intelligence (AI), which is broadly defined as any method that enables intelligent behavior in computers. Topics may include machine learning, probabilistic methods, representation learning, natural language processing, computer vision, and special topics. The course will cover technical concepts, intuitions, and algorithms and will include basic training in AI research.
Required Text(s):
None.
Recommended Text(s):
- Deep Learning (www.deeplearningbook.org) , Goodfellow, Ian; Bengio, Yoshua; Courville, Aaron , MIT Press , 2016 , ISBN No. 0262035618
- Machine Learning: A Probabilistic Perspective (e-book available through Purdue Libraries) , Murphy, Kevin , MIT Press , 2012 , ISBN No. 0262018020
- Python Data Science Handbook (available online at https://jakevdp.github.io/PythonDataScienceHandbook/) , 1st Edition , VanderPlas, Jake , O???Reilly Media Company , 2016 , ISBN No. 1491912057
Learning Outcomes
A student who successfully fulfills the course requirements will have demonstrated:
- The ability to write programs for artificial intelligence techniques.
- The ability to modify or implement one current artificial intelligence research method
- The ability to write a report on a current artificial intelligence research topic.
Lecture Outline:
Topic | |
---|---|
1 | Introduction to artificial intelligence |
2 | Machine learning basics |
3 | Deep learning basics |
4 | Clustering |
5 | Dimensionality reduction |
6 | Density estimation |
7 | Deep generative models |
8 | Special topics |
9 | Project presentations |
Assessment Method:
Quizzes, homework, programming assignments, research-based project. (4/2023)