Works through the fundamental skills of data representation, error measurement, constant prediction rules, and related topics.
Past due
Due Sep 29
View assignment
Introduces the notion of making predictions using features, how to encode data into useful features, multiple regression, and classification via logistic regression.
Available
Due Oct 13
View assignment
Discusses representations for natural language data, and how to make it amenable to making predictions. Introduces methods like n-gram models, TF-IDF, truncated singular value decomposition and latent semantic analysis, working with larger datasets, and hyperparameters.
Upcoming
Opens Oct 12
Two-part assignment. The first introduces more expressive models, via implementing simple neural networks. Also introduces automatic differentiation. The second part studies predicting with little to no labeled data at all using pretrained language models as zero-shot and few-shot predictors. Introduces in-context learning and calibration methods.
Upcoming
Opens Oct 26
Introduces benchmarks, uncertainty quantification, and deployment-relevant considerations such as distribution shift. The goal of this assignment is to prepare students for real-world deployments of predictors which they can now use.
Upcoming
Opens Nov 2