Course Description

Introduction to basic methods and techniques in Machine Learning, Natural Language Processing, and Deep Learning. Will begin with an overview of Probability, Linear Algebra, and Calculus necessary for the later topics. Some methods include Linear/ Logistic Regression, Naive Bayes, Language Modeling, and several Neural Network architectures. Applications include (but not limited to) Computer Vision, Information Retrieval, and Robotics. The main goal of this course is to prepare students for graduate-level Artificial Intelligence classes and potential research opportunities.

Class Time and Location

Winter Quarter (January - March, 2015).
Lecture: Tuesday, Thursday 5:00-6:50
College of Creative Studies, Room 494

Office Hours


Contact Info


Schedule and Syllabus

*Subject to Change

Event TypeDateDescriptionCourse Materials
Lecture Jan 5 Probability Review; Basic Text Processing [Probability Slides]
[Gaussian Distribution Sample Demo]
[Stanford CS229 Probability Review Notes]

[Basic Text Processing Slides]
[Text Processing Demo & Notes]
Lecture Jan 7 Linear Algebra Review; Edit Distance [Linear Algebra Review Slides]
[Stanford CS229 Linear Algebra Review Notes]

[Edit Distance Slides] [Edit Distance Demo]
Lecture Jan 12 Linear Algebra, Multivariable Calculus [Linear Algebra Slides]

[Multivariable Calculus Slides]
Lecture Jan 14 Linear Regression [Linear Regression Slides]
[Stanford CS229 Linear Regression Notes]
[MIT Linear Algebra Video Lectures]
Lecture Jan 19 Logistic Regression, Language Modeling [Logistic Regression Slides]
[Stanford CS229 Logistic Regression Notes]

[Language Modeling Slides]
Lecture Jan 21 Spelling Correction, Statistical Decision Theory [Spelling Correction Slides]

[Statistical Decision Theory Slides]

Lecture Jan 26 Generative and Discrimative, Naive Bayes [Generative v. Discriminative Slides]
[Stanford CS229 Gen v. Dis Notes]

[Naive Bayes Slides]

Learning about Datasets Conversations
Guest Lecture: Kevin Malta Jan 28 Decision Trees and Ensemble Methods [Decision Trees Slides]

[Ensemble Methods Slides]
[Kevin's Slides]
Lecture Feb 4 Information Retrieval [Information Retrieval Slides 1]
[Information Retrieval Slides 2]
Lecture Feb 9 Word Semantics [Word Semantics Slides]
Lecture Feb 11 Optimization [Optimization Slides]
Lecture Feb 16 Hidden Markov Models [HMM Slides]
Lecture Feb 18 Support Vector Machines [SVM Slides]
[Stanford CS229 SVM Notes]
[SVM Demo]
Lecture Feb 23 Word Embeddings: word2vec, GloVe [Word Embeddings Slides]
Lecture Feb 25 Perceptron / FFNN / MLP [Neural Nets Slides]
Lecture Mar 1 BackProp / Convolutional Neural Network
Guest Lecture: Luca Foschini Mar 3 Medical Machine Learning [Behavioral Phenotyping of Digital Health Tracker Data]

[Fully Bayesian Unsupervised Disease Progression Modeling]
Lecture Mar 8 Course Evaluation and Next Steps [Course Evaluation]
Lecture Mar 10 Good Luck on Finals! [Going Forward]