STAT 451: Tentative Schedule

DO NOT RELY ON THIS ROUGH DRAFT.
An official version will be posted by 1/21/25.

(Syllabus)

Day #: Date	Subject	Homework Due (11:59 p.m.)
1: Tu 1/21/25	Help with Anaconda installation 01 Introduction (6): course overview; SVM 01 Python as a Calculator (1)	Read introductory email Q00: background survey (extended to Tu 2/4 to accommodate Fr 1/31 add class deadline)
2: Th 1/23	02 Juypter Lab (4) (JupyterExample.ipynb/.html) 02 Juypter Lab (4) 01 Introduction, continued: SVM	Q01: calculator (extended to 2/4) (login help)
3: Tu 1/28	(01separatingHyperplane.ipynb/.html) [02 Notation and Definitions: optional reading] 03 Sequences (2) (stringsDemo.ipynb, TuplesListsDemo.ipynb)	Q02: Jupyter (extended to 2/4)
4: Th 1/30	03 Fundamental Algorithms, Part 1: linear regression (4) (03linearRegression.ipynb/.html) Discuss HW01
5: Tu 2/4	(04_numpy was here, but I am a little behind my planned schedule)	Q03: sequences
6: Th 2/6	04_NumPy (2) (04_numpy.ipynb/.html) 03 Fundamental Algorithms, Part 2: logistic regression: logistic regression (4) (03logisticRegression.ipynb/.html)	HW01: SVM, linear regression
7: Tu 2/11	05 pandas (2) (05_pandas.ipynb/.html)	Q04: NumPy
8: Th 2/13	continue 05_pandas from value_counts() (8:00), Create(?) (11:00) 03 Fundamental Algorithms, Part 3: decision tree (4) (03decisionTree.ipynb/.html)	(Q05 pandas was here)
9: Tu 2/18	06 matplotlib (3) (06_matplotlib.ipynb/.html) continue decision tree	Q05: pandas
10: Th 2/20	03 Fundamental Algorithms, Part 4: more on SVM (4) (03SVM.ipynb/.html)	HW02: logistic regression, decision tree
11: Tu 2/25	03 Fundamental Algorithms, Part 5: k-NN (2) (03kNN.ipynb/.html) (07 write functions was here)	Q06 matplotlib
12: Th 2/27	07 write functions (2) 04 Anatomy of a Learning Algorithm (4): gradient descent, scikit-learn (04gradientDescent.ipynb/.html)
13: Tu 3/4	05 Basic Practice, Part 1: feature engineering (6) (05featureEngineering.ipynb/.html)	Q07 functions
14: Th 3/6	Discuss exam rules 08 conditional expressions (2) 05 Basic Practice, Part 2: algorithm / data split / model fit / regularize (4) (05modelFitRegularize.ipynb/.html)	HW03: more SVM, kNN, gradient descent, feature engineering
15: Tu 3/11	discuss project (optional) Q&A review	Q08 conditional expressions
16: Th 3/13	Midterm exam in class	Midterm exam
17: Tu 3/18	05 Basic Practice, Part 3: assessment / hyperparameter tuning / cross-validation (5) (05assessmentTuningCV.ipynb/.html)	Project: form a group
18: Th 3/20	Review project groups 05 Basic Practice, Part 3, continued: tuning & CV 07 Problems and Solutions, Part 1: kernel regression (1) (07kernelRegression.ipynb/.html)
[Tu 3/25, Th 3/27]	[no class: spring break]
19: Tu 4/1	07 Problems and Solutions, Part 2: multiclass, one-class, and multilable classification (4)	HW04: feature engineering, data split, model fit and regularization
20: Th 4/3	07 Problems and Solutions, Part 3: ensemble learning (3) (07ensemble.ipynb/.html) regular expressions (I had extra time and introduced regular expressions because our 9/5/24 survey revealed interest. They are not on the exam.)	Project: proposal
21: Tu 4/8	schedule feedback meetings 08 Advanced Practice: 08.pdf (5): imbalance, combining/stacking, efficiency, multicore (08imbalance_stacking_timing_multicore.ipynb/.html)
22: Th 4/10	project proposal feedback: meet in class with teacher and/or TA	Project proposal feedback meeting HW05: algorithm selection, multiclass classification, assesment, tuning, ensemble learning, imbalance
23: Tu 4/15	09 Unsupervised Learning: 09.pdf (7) (09densityEstimation.ipynb/.html, 09clustering.ipynb/.html, 09PCA.ipynb/.html)
24: Th 4/17	presentation schedule 09 Unsupervised Learning, continued: PCA project help	Mo 4/21: Project: turn in slides
25: Tu 4/22	project help
26: Th 4/24	Project: first 1/2 of presentations	Project: peer feedback on first 1/2
27: Tu 4/29	Project: second 1/2 of presentations	Project: peer feedback on second 1/2
28: Th 5/1	(optional) Q&A review	Project: report; peer feedback (2-3 sentences) due Fr 5/2
Su 5/4	Final exam: 7:45-9:45 a.m.	Final exam

Note:

• Black lines in this schedule correspond to materials on machine learning. A black number at the start of a phrase, like the "01" in "01 Introduction", indicates a chapter in the optional reference book, The Hundred-Page Machine Learning Book by Andriy Burkov.
• Orange lines correspond to materials on Python basics, which we study to allow using the scikit-learn library to apply machine learning techniques to real data.
• A number in parentheses, like "(2)", indicates the number of pages in a handout to help me with planning.