Track 1
Machine learning techniques
Visualization or interpretation of representations
Unsupervised, semi-supervised, and supervised representation learning
Representation and reinforcement learning
Deep learning theories and practices
Computer vision and natural language processing
Hierarchical models and optimization methods for learning
Interpretability and explainability of AI algorithms

Track 2
Adaptive data analysis and selective inference
Robustness of learning algorithms to adversarial attacks
Learning with combinatorial and algebraic structure
Game theory and learning
Learning from complex data sources e.g., time series, networks
Probabilistic graphical models and learning
Reinforcement learning and Interactive learning, and control
Multi-Strategy Learning (MSL) in distributed and streaming environments