CS181: Machine Learning

Harvard University

Course Info

Instructors
  • David Parkes
    OH: Mon 1-2p, Thur 2:30-3:30, 5.15-6p, MD 229
  • Alexander "Sasha" Rush
    OH: Wed 2:30-4, MD 217
  • Email: Piazza preferred or cs181 at seas.harvard.edu (instructors only)
Lectures
Teaching Assistants
  • Shai Szulanski, Jeffrey Ling, Samuel Cheng, Ankit Gupta, Aidi Zhang, Lily Zhang, Frances Ding, Mark Goldstein, Charles Liu, Jeffrey Chang, Rachit Singh, Joseph Song, Fanney Zhu, Christine Hwang, and Carl Denton
Forum and Announcements
Office Hours
  • Tue 8-10pm: Quincy DH
  • Wed 6-8pm: MD 119 / Second Floor
  • Wed 8-10pm: Lowell DH
  • Thu 8-10pm: Currier DH
  • Thu 8-10pm: Eliot DH
  • Fri 10-Noon: MD First Floor Lounge (one floor above ground!)
References
Section Times
  • Mon, 4-5,5-6:30p(extended): MD 119
  • Tues, 4-5:30p(extended): Northwest Basement (B105)
  • Wed, 4-5,5-6p: MD 119
Syllabus and Collaboration Policy
Links

Schedule

Date Area TopicDemos ReadingsAssignment (DUE: Fri 5pm of this week)
Jan. 24 Machine Learning
Jan. 26 Regression Linear Regression 1 Regression Bishop § 3.1, Sklearn § 3.1, 18.10
Jan. 27 Section 0 Math Review
Jan. 30 Section 1 Linear Reg ( sol )
Jan. 31 Linear Regression 2 Gaussian
BasisRegression 		Bishop § 2.3, 3.1 T1 Regression (submit | self-grading)
Feb. 2 Model Regularization Model Selection
Feb. 6 Section 2 Model Selection (sol) Sklearn
Feb. 7 Bayesian Linear Regression Bishop § 3.3 P1 Regression (submit | kaggle)
Feb. 9 Classification Linear Classification Perceptron Bishop § 4.1, Sklearn § 15.9
Feb. 13 Section 3 Bayes Classification (sol)
Feb. 14 Probabilistic Classification Probabilistic Classification Bishop § 4.2, 4.3, Sklearn § 18.1, 29.24
Feb. 16 Neural Networks Neural Networks 1 Neural Networks 1
TF Playground 		Bishop § 5.1-5.2
Feb. 20 Section 4 Probabilistic Classification & NN1 (sol)
Feb. 21 Neural Networks 2 Neural Networks 1
ConvNet JS 		Bishop § 5.3 T2 Classification (submit | self-grading | soln)
Feb. 23 Margin-Based Models Margin-Based Classification Bishop § 7.1
Feb. 27 Midterm Review Topics Practice Problems | Solutions
Feb. 28 Support Vector Machines Bishop § 7.1
Mar. 2 Midterm 1
Mar. 6 Section 5
Support Vector Machines (sol)
Mar. 7 Unsupervised Hierarchical Clustering, K-Means Bishop § 9.1 P2 Classification (submit | kaggle)
Kaggle due Th 11:59pm
Competition ends W 11:59pm
Mar. 9 Topics 1 Deep Learning for Text Deep NLP Tutorial (optional)
Mar. 20 Section 7 Clustering
(demo) (sol)
Mar. 21 Mixture Models, EM Bishop § 9.2,9.3 T3 SVMs (submit)
Mar. 23 Discrete Mixtures, Topic Models Topic Modeling Bishop § 9.3.3,
Introduction to Probabilistic Topic Models (optional)
Mar. 27 Section 8
EM and Topic Modeling (sol)
Mar. 28 Dimensionality Reduction PCA Bishop § 12.1 T4 Clustering/EM (submit)
Mar. 30 Graphical Models HMMs
Apr. 3 Section 9
PCA + HMMs (sol)
Apr. 4 Bayesian Networks P3 Recommendation (submit | kaggle)
Apr. 6 Inference
Apr. 10 Section 10
Bayesian Networks (sol)
Apr. 11 Reinforcement Learning MDP / Value and Policy Iteration T5 HMM/MDP (submit)
Apr. 13 Reinforcement Learning
Apr. 17 Section 11 MDP and RL (sol)
Apr. 18 Deep RL
Apr. 20 Topics 2 Learning Theory (a)
Learning Theory (b)
Apr. 23 Midterm Review Topics | Practice Problems | Solutions
Apr. 25 Midterm 2 P4 RL (submit)

Grading

Grades are determined by four aspects of the class:

  • Four Practicals [P] (30%)
  • Five Homeworks [T] (30%)
  • Midterm Exam 1 (20%)
  • Midterm Exam 2 (20%)