Explore effective strategies for handling imbalanced datasets using the Label-Distribution-Aware Margin Loss in this informative 23-minute lecture from the University of Central Florida. Gain insights into the challenges posed by data imbalance, understand existing solutions, and delve into experimental results that demonstrate the effectiveness of this novel approach. Learn how to improve model performance on imbalanced datasets, a common issue in real-world machine learning applications.
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
University of Central Florida via YouTube
Overview
Syllabus
Introduction
What is data imbalance
Existing solutions
Experiments
Summary
Taught by
UCF CRCV
Tags
Related Courses
-
Understand data science for machine learning
-
Operationalizing Data-Centric AI - Practical Tools to Quickly Improve ML Datasets
-
Prioritized Training Using Reducible Holdout Loss Selection (RHO-LOSS) - Accelerating Machine Learning
-
Robust Deep Learning Under Distribution Shift
-
Joint Tensor Alignment and Coupled Factorization
