Skip to Content
Course

Introduction to Deep Learning for Computer Vision

CSE-41388

Understanding How Deep Learning Powers Visual Intelligence

Deep learning has transformed computer vision by enabling machines to interpret and understand information from images and videos. These capabilities support applications in autonomous systems, healthcare, robotics, augmented reality, intelligent imaging, and visual content analysis.

This course provides a practical introduction to the foundations of deep learning, with a strong focus on computer vision. You will begin with image representation, neural network fundamentals, model training, and hyperparameter tuning before progressing to convolutional neural networks and modern approaches to visual understanding.

The course explores important computer vision tasks such as image recognition, object detection, image segmentation, and image restoration. You will be also introduced to attention-based architectures and selected emerging topics in deep learning. Through conceptual instruction and hands-on programming assignments, you will gain experience designing, training, evaluating, and improving deep learning models for practical visual applications.


Course Highlights

  • Deep learning foundations and neural network concepts for computer vision
  • Image representation and data preparation through visualization, preprocessing, and dataset organization
  • Convolutional neural networks (CNNs) for extracting image features and recognizing visual content
  • Core computer vision applications including image recognition, object detection, image segmentation, and image restoration
  • Attention-based architectures and emerging approaches in modern computer vision
  • Model improvement and evaluation through data augmentation, transfer learning, hyperparameter tuning, quantitative metrics, visualization, and error analysis
  • Hands-on model development in Python and PyTorch using real image datasets, from training and validation to testing and inference

Course Benefits

  • Develop a solid foundation in deep learning concepts for computer vision
  • Gain hands-on experience building and training models with Python and PyTorch
  • Become familiar with common computer vision tasks, including image recognition, object detection, image segmentation, and image restoration
  • Practice improving model performance through data preparation, augmentation, transfer learning, and hyperparameter tuning
  • Learn to evaluate model results using quantitative metrics, visualizations, and basic error analysis
  • Gain experience working with real image datasets in a cloud-based programming environment
  • Build foundational knowledge for further study and professional development in artificial intelligence, machine learning, and computer vision
  • Apply eligible course credit toward an academic degree or professional credential, subject to approval by the receiving institution

Course Details and Next Steps

  • Course typically offered: Online during our Winter, Spring, Summer, and Fall academic quarters
  • Prerequisites: Basic proficiency in Python programming, college-level calculus, linear algebra, probability, and statistics
  • Next steps: Continue your learning with Machine Learning Methods or pursue the Technical Aspects of Artificial Intelligence certificate program 
  • Contact: For more information about this course, please email unex-techdata@ucsd.edu
     

Who Should Take This Course?

  • Aspiring machine learning and computer vision engineers
  • Data scientists and AI practitioners
  • Software developers interested in image and video analysis
  • University students in computer science, engineering, or related fields
  • Researchers exploring deep learning applications
  • Professionals seeking practical skills in computer vision and neural networks

Course Information

Online
3.00 units
$850.00

Get more information

This course applies to these programs

Technical Aspects of Artificial Intelligence Machine Learning Methods

Course sessions

Closed

Section ID:

198421

Class type:

Online Asynchronous.

This course is entirely web-based and to be completed asynchronously between the published course start and end dates. Synchronous attendance is NOT required.
You will have access to your online course on the published start date OR 1 business day after your enrollment is confirmed if you enroll on or after the published start date.

Textbooks:

All course materials are included unless otherwise stated.

Policies:

  • No refunds after: 6/29/2026

Schedule:

No information available at this time.
Closed

Instructor: Chung-Chi Tsai

Chung-Chi Tsai
Chung-Chi-Tsai-128826.jpg

Dr. Charles Tsai holds a B.S. degree in Electrical Engineering from National Tsing-Hua University in Taiwan. He furthered his education with an M.S. degree from the University of California, Santa Barbara, and a Ph.D. from Texas A&M University. During his academic journey, Dr. Tsai received a full scholarship from the Ministry of Education, Taiwan, to participate in a one-year exchange program at the University of New Mexico. Currently, Dr. Tsai works as a vision and image processing R&D engineer in the industry. In addition, he actively serves as the top-tier conference and journal reviewer in the field of computer vision. His research interests focus on image restoration and computer vision applications for low-latency and low-power camera systems.

 
Full Bio