Research Computing Center

Unsupervised Learning in Computer Vision

Unsupervised learning methods are playing an  increasingly vital role in  the field of computer vision enabling algorithms to discover patterns in data without being given predefined categories or target outputs. These techniques are driving breakthroughs in areas such as image segmentation,  dimensionality reduction, and anomaly detection.  

The workshop will introduce participants to unsupervised learning techniques and their applications in computer vision, with a focus on anomaly detection. Through hands-on exercises, participants will gain practical experience applying these methods to detect anomalies in medical images using PyTorch. 

Objectives:

• Understand the fundamentals of unsupervised learning in computer vision applications.

• Explore anomaly detection, a key skill for identifying outliers, uncovering fraud, correcting  data errors, and  recognizing unusual patterns. 

• Implement unsupervised anomaly detection in medical images through hands-on exercises using PyTorch. 

Level: Intermediate

Duration: 2 hours

Prerequisites: A basic understanding of machine learning concepts as well as experience with Python programming are essential. Experience with a machine learning library, such as PyTorch is required. Participants are encouraged to bring their laptops for an engaging and immersive learning experience. An RCC account is optional.