Home

Lectures

Dates	Lecture	References
Aug 26	course overview	ISLP† Ch 1, Statistical learning problems slides
Aug 28	supervised learning	ISLP Ch 2, Supervised learning slides, Bias-variance decomposition derivation
Sep 4, 9	linear regression	ISLP Ch 3, Linear regression slides, Least squares as maximum Gaussian likelihood
Sep 11	logistic regression	ISLP Ch 4, Classification slides, Logistic regression as maximum Bernoulli likelihood
Sep 16, 18	video lectures Discriminant analysis lecture video, Naive Bayes lecture video	ISLP Ch 4, Classification slides, Naive Bayes with the categorical event model notes
Sep 23	(cross) validation	ISLP Ch 5, Cross validation and the bootstrap slides
Sep 25	the bootstrap	ISLP Ch 5, Cross validation and the bootstrap slides
Sep 30	subset selection, training error adjustments	ISLP Ch 6, Model selection slides, Mallow's \(C_p\) derivation
Oct 2	shrinkage methods	ISLP Ch 6, Model selection slides, Review of the method of Lagrange multipliers
Oct 7	support vector machines (SVM)	ISLP Ch 9, SVM slides, SVM problem derivation,
Oct 9	kernel trick, kernelized SVMs	ISLP Ch 9, SVM slides, SVM dual problem derivation
Oct 16	video 2x lecture Non-linear models lecture video	ISLP Ch 7, Moving beyond linearity slides
Oct 21	degrees of freedom	Degrees of freedom notes
Oct 23	tree-based methods	ISLP Ch 8, Tree-based methods slides, Gradient boosting notes
Oct 28	multilayer perceptrons (MLPs)	D2L‡ Ch 5, §11.3-5, MLP slides
Oct 30	training (deep) neural nets	D2L‡ Ch 5, §11.3-5, Training neural nets slides, Andrew Ng's notes on VC dimension
Nov 4	video 2x lecture (Out-of-distribution) generalization lecture video	D2L §3.6, §4.7, Generalization slides
Nov 6	midterm
Nov 11	convolutional neural net (CNN) basics	D2L Ch 7, CNN basics slides, Convolution demo, LeNet demo, World War I: The Seminal Tragedy
Nov 13	video 2x lecture Modern CNNs lecture video	D2L Ch 8, Modern CNN slides
Nov 18	transfer learning, style transfer	D2L §14.1-2, §14.12, Transfer learning slides, Fine-tuning demo, Style transfer demo
Nov 20	object detection	D2L §14.3-8, Object detection slides
Nov 25, Dec 2	video 2x lectures Clustering lecture video, Principal components analysis (PCA) lecture video	ISLP Ch 12, Unsupervised learning slides
Dec 4	video 2x lecture Sequence modeling lecture video, Recurrent neural nets (RNNs) lecture video	D2L Ch 9, §10.1-3, Sequence models slides, RNN slides, Language statistics demo, RNN demo, deep RNN demo
Dec 9	video lecture attention, transformers	Transformers slides, tinygpt repo

†ISLP refers to Introduction to Statistical Learning with Applications in Python.
‡D2L refers to Dive into Deep Learning.

Labs

Date	Lab	References
Aug 27	linear algebra review, probability review	Linear algebra review slides, Probability review slides, EECS 398 Linear Algebra Review
Sep 3	Intro to Python	ISLP §2.3, Introduction to Python lab
Sep 10	Linear regression lab	ISLP §3.6, Linear regression lab
Sep 17	K-nearest neighbors, logistic regression	ISLP §4.7, Classification lab
extra lab	PyTorch quickstart video	PyTorch quickstart notebook, PyTorch's Introduction to PyTorch Tensors (watch after watching quickstart video)
Sep 24	linear & quadratic discriminant analysis, naive Bayes, least squares in PyTorch	ISLP §4.7, Classification lab, Least squares in PyTorch
Oct 1	Cross-validation and the Bootstrap lab	ISLP §5.3, Cross validation and the Bootstrap lab
Oct 8	Linear models selection and regularization lab	ISLP §6.5, Linear Models and Regularization Methods lab
Oct 22	SVM lab	ISLP §9.6, SVM lab
Oct 29	Tree-based methods lab	ISLP §8.3, Tree-based methods lab
Nov 5	midterm review
Nov 12	MLP demos	Perceptron demo, MLP from scratch, Weight decay demo
Nov 19	Predicting house prices on Kaggle	D2L §5.7, Predicting house prices on Kaggle
Nov 26	CNN demos	AlexNet demo, GoogLeNet demo, ResNet demo
Dec 3	Unsupervised learning lab	ISLP §9.6, Unsupervised learning lab