IDS705

Automating prediction and decision-making based on data and past experience. Students will learn how and when to apply supervised, unsupervised, and reinforcement learning techniques, and how to evaluate performance. Common pitfalls such as overfitting and data leakage will be explored and how they can be avoided. Topics include model flexibility and regularization; common supervised learning models and ensembles; performance evaluation techniques; dimensionality reduction; clustering; and the fundamentals of reinforcement learning. Open only to Interdisciplinary Data Science students.

Spring Only

No Special Consent Required