CS6140 schedule

CS6140/4420 Machine Learning Section 3, Fall 2026

Week / Assignment	Topic / Lecture	Other Reading
9/10 - 9/17 Week 1: Intro, Regression HW 1 — Due: 9/22	Intro LinReg LinReg Intro LinReg Ridge Intro Regression Regression, Advanced Topics (optional) Slides Lecture 1 Lecture 2 Normalization: When to Use What	Background: Probabilities Convexity1 Convexity2 Linear algebra Programming: MATLAB, Java, Python, R DHS 8.1-8.5 KMPP ch 16.2 DHS ch 5 (up to 5.4.2) KMPP ch 7 (up to 7.5) Lasso Coordinate Descent (notebook) — from-scratch demo, checked against sklearn, regularization path (lecture demo, not graded)
9/17 - 9/24 Week 2: Decision Trees, Boosting, Features	DT DT Boosting KNN Decision Trees Distances and Similarities KNN Local Classifiers	DHS ch 9, 9.5 KMPP ch 16, 16.6, 27.6.2 AdaBoost: Slides \| Boosting the Margin \| Additive Logistic Regression \| AdaBoost/Hedge Margins and Feature Analysis for Boosting RankBoost LambdaMART JForests: Paper \| Code XGBoost Bagging ECOC: Lecture \| Slides \| Paper Active Learning: Notes \| Slides VC Dimension: Wikipedia \| Slides
9/24 - 10/1 Week 3: Gradient Descent HW2 — Due: 10/6 Project Proposal — Due: 10/13	GD LogReg GD LogReg Gradient Descent, Logistic Regression Logistic Regression, Newton Lecture 3 Lecture 4 Boosting	DHS ch 5 KMPP ch 7, 8 Newton's Method Logistic Regression
10/1 - 10/8 Week 4: Perceptron, Regularization	Perceptron Lecture 5 The Perceptron Regularization (Stanford) Regularized Logistic Regression (Ng) Regularized Logistic Regression (Ng)	Logistic Regression: Loss Functions, Convexity, Feature Selection
10/8 - 10/15 Mon 10/12: no class (Indigenous Peoples' Day) Week 5: PCA, Features, Kernels Mon 10/12: Indigenous Peoples Day, NO CLASS HW3 — Due: 10/20	PCA Margins Kernel KernelPCA PCA and Feature Representations Lecture 17 PCA, LDA Kernels and Kernelized Algorithms Lecture 7 Lecture 8 Lecture 9	PCA: DHS ch 10 KMPP ch 12 (PCA), ch 14 (kernels) Bishop PRML ch 6 (kernels), ch 12 (PCA) ESL §14.5 (PCA) A Tutorial on PCA (Shlens) Haar Features: Wikipedia \| Slides \| Paper tSNE: Slides \| Paper \| Code \| Gradient Derivation (optional) \| How to Use t-SNE Effectively Feature Engineering: Article \| Slides (Princeton) \| Slides (Berkeley) Kernel Methods: Slides \| Primer \| Paper \| Random Features (Rahimi & Recht)
10/15 - 10/22 Week 6: Kernels (cont.), SVM	SVM SVM SVM with Kernels SVM: Advanced Topics (optional) Convex and Constrained Optimization (optional) SVM demo: support vectors and their α's during SMO (3-D toy data) \| video (SMO) \| video (QP solver) Lecture 5-6	DHS ch 5.11 KMPP ch 14 Bishop PRML ch 7 ESL ch 12 Books: Bishop PRML \| ESL Optimization: Constrained (slides) SMO: Notes (Stanford) \| Paper (Platt) Saddle-point SVM Tutorial (Burges) A Practical Guide to SVM Classification (LIBSVM) SVM: Wikipedia \| SVM and VC Dimension \| Notes (Ng) \| Book chapter (ML in Action)
10/22 - 10/29 Week 7: Generative HW 4 — Due: 11/3 Project Checkpoint — Due: 11/10	GDA NaiveBayes Generative Classifiers: Fitting Densities, GDA, and Naive Bayes Bayesian Linear Regression Generative Classifiers: Advanced Topics (optional) Lecture 9 Lecture 10	DHS ch 2, 3 KMPP ch 2, 3, 4 Probability Primer (prerequisite) Slides: Generative Intro \| GDA \| Naive Bayes GDA, Naive Bayes (Ng) Naive Bayes and Logistic Regression (CMU) Smoothing Maximum Likelihood Naive Bayes Multivariate Normal: Wikipedia \| Marginal/Conditional Correlation Coefficient
10/29 - 11/5 Week 8: Generative, EM	GMM GMM Mixtures Mixture Models and the EM Algorithm EM Theory and Latent-Variable Models (optional) Lecture 11+12 Lecture 13	KMPP ch 20, KMPP ch 11(EM) EM (MIT slides) EM: Example \| Wikipedia \| Notes (Berkeley) \| Notes (other) \| Slides (other) Graphical Models: Factor Graphs (optional) \| Slides (Bishop) \| Book (Bishop) \| Video (Bishop): Part 1, Part 2, Part 3
11/5 - 11/12 Week 9: Neural Networks, Backprop, Autoencoders HW5 — Due: 11/17 NN Setup (HW5–7, do before HW5)	NN AutoEnc Neural Networks: The Basics Neural Networks: Advanced Topics (optional) Lecture demo (notebook) · notebook + playground (zip, runs locally) CS6140 Neural Network Playground Lecture 18: NN Basics Intro to Neural Networks Visualizer : Neural Networks Activation Function Table Lecture 19: AutoEncoderNN, Word Vectors_NN, Activation	DHS ch 6 Activation functions table Dropout (Srivastava, Hinton et al.) Neural network toy example Other slides (Mitchell) Backpropagation: Rumelhart, Hinton & Williams (1986)
11/12-11/19 Week 10: Generative Neural Networks: VAE, GAN	Variational Autoencoders (VAE) VAE lecture demo (notebook) Generative Adversarial Networks (GAN) GAN lecture demo (notebook)	GANs (d2l 20.1) \| DCGAN (d2l 20.2) Kingma & Welling, VAE \| Goodfellow, GAN tutorial
11/19 - 11/26 Week 11: Adv NN, CNN HW6 — Due: 12/1 Project Report — Due: 12/8	AdvNN CNN Convolutional Networks: From Sliding Windows to ResNets Convolutional Networks: Advanced Topics (optional) Lecture demo (notebook) Lecture 7/23 : Adv NN intro Lecture 7/25 : Convolution NNets (d2l slides w/ annotations)	basic CNN (d2l html+ pytorch) Modern CNN (d2l html+ pytorch) Image augmentation, fine-tuning (d2l)
11/26-12/3 Thu 11/26: no class (Thanksgiving break, 11/25–11/29) Week 12: RNN, LSTM, Seq2Seq	RNN Seq2Seq Recurrent Networks: Language Models, Gates, and Translation Recurrent Networks: Advanced Topics (optional) Lecture demo (notebook) Lecture 7/30 : Recurrent NNets, LSTM, GRU (d2l slides w/ annotations) Lecture 8/1 : RNN : Encoder-Decoder, Seqence-to-Sequence, Machine Translation (d2l slides w/ annotations)	RNN (d2l html+ pytorch) RNN-Modern (d2l html+ pytorch)
12/3 - 12/10 Week 13: Tokens, Word Vectors, Attention HW7 — Due: 12/15	Word2Vec Attention Tokens and Word Vectors: Subwords, BPE, and word2vec Tokens and Word Vectors: Advanced Topics (optional) Lecture 8/13 : NLP, Word-To-Vec, Glove Embedding (d2l slides w/ annotations) Attention: Queries, Keys, and Values Lecture demo (notebook) Lecture 8/6 : Attention Mechanic (d2l slides w/ annotations)	Simple Word-2-Vec tutorial NLP, Word Embedding (d2l html+ pytorch); BPE (d2l 15.6)
12/10 - 12/17 Week 14: Transformers, GPT	Transformer The Transformer and GPT: From Encoder–Decoder to Decoder-Only Transformers: Advanced Topics (optional) Lecture demo (notebook) Lecture 8/8 : Self Attention & Transformers (d2l slides w/ annotations)	Attention and Transformers (d2l html+ pytorch) nanoGPT (Karpathy)
Final Exam tentative: Thu Dec 17, 11:45am–2:45pm	Final Exam: theory, on paper, in class. You may bring your own written notes; no devices allowed. Do not expect pure math derivations/calculations. Instead, expect questions on key algorithmic points related to class material, and possible simple modifications for a specific purpose.