Skip to main content

🏢 Queen's University

Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
·1620 words·8 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 Queen's University
Researchers unveil the Infeasibility Theorem, proving optimal class-incremental learning is impossible with discriminative models due to task confusion, and the Feasibility Theorem, showing generative…
Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
·3043 words·15 mins· loading · loading
Machine Learning Representation Learning 🏢 Queen's University
Boost time-series model accuracy with Segment, Shuffle, and Stitch (S3)! This simple layer shuffles data segments to enhance representation learning, improving classification, forecasting, and anomaly…