March 2
@
8:00 am
–
March 31
@
5:00 pm
Self-Supervised Learning
Dive into the cutting-edge world of self-supervised learning (SSL) for computer vision in this dynamic and hands-on course. SSL is revolutionizing AI by enabling models to learn from vast amounts of unlabeled data, making it a true game-changer.
In this course, you’ll explore popular SSL methods like SimCLR, MoCo, BYOL, and Vision Transformers (DINO), while gaining hands-on experience using PyTorch to build and train your own models. Engage in interactive coding sessions and apply SSL techniques to real-world datasets through project-based assessments, ensuring you gain both theoretical knowledge and practical expertise. Whether you’re an AI enthusiast or a professional looking to advance your skills, this course will equip you with the tools to create more efficient and scalable computer vision models. Join us and be at the forefront of AI innovation!
Course At a Glance
Instructional Period: March 2 – March 31, 2026
Time to Complete Badge: 60 days
Last Day to Earn Badge: April 31, 2026
Expertise Level: Intermediate/Advanced
Scientific Machine Learning
Parallelism in Deep Learning
- Basic Python programming
- Basic understanding of deep learning
- Basic understanding of graphical concepts
- Basic PyTorch programming
Audience: This course is aimed at software engineers, data scientists, data engineers, data analysts, research scientists, and developers who wish to advance their understanding of computer vision. Previous participants have included professionals from leading technology and agritech companies.
By the end of the course, you should be able to:
Analyze the principles, classical methods, and recent advancements in self-supervised learning (SSL) and their applications in computer vision.
Implement self-supervised learning (SSL) methods, including contrastive, clustering-based, and generative approaches, using PyTorch.
Evaluate self-supervised learning (SSL) models for various downstream tasks such as image classification, object detection, and segmentation.
Describe advanced self-supervised learning (SSL) techniques, future trends, and their applications in different domains of computer vision
- 1. 3 Quizzes: Test comprehension of fundamental self-supervised learning concepts.
- 2. 1 Coding Assignment: Implementing both classical and state-of-the-art SSL methods. Also, fine-tuning SSL models for different downstream tasks and evaluating their performance.
Module 1: Fundamentals of Self-Supervised Learning
Module 2: Implementation of SSL Methods
Module 3: Applying SSL Models to Downstream Tasks
Module 4: Advanced SSL Techniques and Future Trends
The course starts on March 1, 2025. All coursework must be completed by April 31, 2025, in order to earn the micro-credential badge. You will continue to have access to the course materials until January 1, 2027. The approximate time to complete this course is 16 hours.
This course has an instructional period from March 2 to March 31, 2025. During this instructional period, course materials will be released weekly and live synchronous sessions will be held. You may complete the course materials at your own pace. Live Zoom meetings will be conducted for interactive coding sessions. A suitable time for these live sessions will be determined through a group poll. The recordings of those sessions will be available soon after each meeting.
You will receive the Self-Supervised Learning micro-credential badge upon successful completion of the course assessments.
Course materials are provided within the course. No additional purchase is required.
Registration
Register for the course as a 1-credit independent study course with a maximum of 3 such TrAC courses per semester.
Students must register for the independent study by emailing benearl@iastate.edu and cc-ing baditya@iastate.edu. Also, fill this Google form for our records: https://forms.gle/d7PUHaqjko6sPHVg7
Note: You cannot cancel your registration after April 1 for any course.
Industry Professionals/ISU Staff/Post Docs
$
500
.00
ISU Professionals/Staff and Government Employees: $300
Zaki Jubery, Data Scientist
Zaki Jubery is a research scientist in the Translational AI Center (TrAC) at Iowa State University. His research interests are in (i) High-throughput phenotyping (ii) Crop modeling (iii) Image processing (iv) Applied machine learning in agriculture.
Zaki works on integrating engineering tools into various agricultural applications. He has been dedicated to pioneering research in this field since September 2013.
Zaki earned his Ph.D. in Mechanical Engineering from Washington State University and completed a postdoctoral fellowship at the University of Illinois Urbana-Champaign. Before transitioning to agriculture, his background includes designing, simulating, and manufacturing point-of-care microfluidics sensors for biomedical and industrial applications.
Nicole Hayungs
nhayungs@iastate.edu
