Changnan Xiao

Artificial Intelligence (4) Machine Learning (4) Core AI (3) Core Methods (3) Learning Types (3) Optimization & Theory (2) Deep Learning (1) Reinforcement Learning (1) Architectures (1) Learning Paradigms (1) Methods (1)

catastrophic forgetting (3) out-of-distribution detection (3) continual learning (3) class-incremental learning (2) chain-of-thought reasoning (1) feature representation (1) exploration exploitation (1) policy iteration (1) prototype-based classification (1) neural collapse (1) behavior policy (1) data distribution (1) length generalization (1) task incremental learning (1) within-task prediction (1) deep reinforcement learning (1) task-id prediction (1) sample efficiency (1) probabilistic modeling (1) structure learning (1)