Machine Learning / 21
Advanced ML
Explore transfer, active learning, weak supervision, distribution shift, and other advanced directions.
This is a knowledge index. Published titles open their articles; the remaining entries outline planned coverage.
Subtopics
- 21.01
Semi-Supervised Learning
Planned guide: Semi-Supervised Learning. Focus on intuition, assumptions, and a worked example.
- 21.02
Self-Supervised Learning
Planned guide: Self-Supervised Learning. Focus on intuition, assumptions, and a worked example.
- 21.03
Transfer Learning
Planned guide: Transfer Learning. Focus on intuition, assumptions, and a worked example.
- 21.04
Active Learning
Planned guide: Active Learning. Focus on intuition, assumptions, and a worked example.
- 21.05
Online Learning
Planned guide: Online Learning. Focus on intuition, assumptions, and a worked example.
- 21.06
Incremental Learning
Planned guide: Incremental Learning. Focus on intuition, assumptions, and a worked example.
- 21.07
Multi-Task Learning
Planned guide: Multi-Task Learning. Focus on intuition, assumptions, and a worked example.
- 21.08
Meta-Learning
Planned guide: Meta-Learning. Focus on intuition, assumptions, and a worked example.
- 21.09
AutoML
Planned guide: AutoML. Focus on intuition, assumptions, and a worked example.
- 21.10
Ensemble Optimization
Planned guide: Ensemble Optimization. Focus on intuition, assumptions, and a worked example.
- 21.11
Weak Supervision
Planned guide: Weak Supervision. Focus on intuition, assumptions, and a worked example.
- 21.12
Synthetic Data for ML
Planned guide: Synthetic Data for ML. Focus on intuition, assumptions, and a worked example.
- 21.13
Distribution Shift
Planned guide: Distribution Shift. Focus on intuition, assumptions, and a worked example.
- 21.14
Domain Adaptation
Planned guide: Domain Adaptation. Focus on intuition, assumptions, and a worked example.
- 21.15
Causal ML
Planned guide: Causal ML. Focus on intuition, assumptions, and a worked example.
- 21.16
Graph Machine Learning
Planned guide: Graph Machine Learning. Focus on intuition, assumptions, and a worked example.


