On the Impact of Class Imbalance on the Learning Dynamics of Deep Neural Networks:An Intuitive Insight
A new research paper explores how class imbalance affects the learning process of deep neural networks. The study demonstrates that imbalanced datasets cause DNNs to underfit minority class samples early in training, focusing primarily on the majority class. While the model eventually learns minority samples, this learning is often overfitted and non-generalizable at the test phase, leading to poor performance. AI
IMPACT Highlights a critical challenge in training AI models, potentially guiding development of more robust and equitable AI systems.