Volume 3: The Modern Frontier: Scale, Intelligence, and What Comes Next3/10
Chapter 03 of 10
Machine Learning 221-230
10 lessons52 min readingParts 221-230
- 01Supervised LearningHow does a model learn from examples with known answers?5 min read5 min read
- 02Unsupervised LearningWhat can a model learn when examples have no supplied labels?5 min read5 min read
- 03Reinforcement LearningHow can an agent learn through actions and delayed rewards?6 min read6 min read
- 04Features and LabelsWhat information goes into a predictive model, and what answer should it learn?5 min read5 min read
- 05Training, Validation, and Test SetsWhy split machine-learning data into separate groups?5 min read5 min read
- 06Overfitting and UnderfittingWhy can a model perform well in training but poorly in the real world?5 min read5 min read
- 07Precision and RecallHow should a classifier be judged when different mistakes have different costs?5 min read5 min read
- 08Bias in Machine LearningHow can a model reproduce unfair or distorted outcomes?5 min read5 min read
- 09Model DriftWhy can a model become less useful after deployment even when its code never changes?5 min read5 min read
- 10MLOpsWhat operational work surrounds a production machine-learning model?6 min read6 min read