2017 Fall

Course Name Time Location Description
CSE 417T: Introduction to Machine Learning T, R

M, W

McMillan G052

Lopata 101

The field of machine learning is concerned with the question of how to construct computer programs that automatically improve with experience. This course is a broad introduction to machine learning, covering the foundations of supervised learning and important supervised learning algorithms. Topics to be covered are the theory of generalization (including VC-dimension, the bias-variance tradeoff, validation, and regularization) and linear and non-linear learning models (including linear and logistic regression, decision trees, ensemble methods, neural networks, nearest-neighbor methods, and support vector machines). Prerequisites: CSE 247, ESE 326, Math 233, and Math 309 (can be taken concurrently).
CSE 511A: Introduction to Artificial Intelligence M, W
Hillman 70 The discipline of artificial intelligence (AI) is concerned with building systems that think and act like humans or rationally on some absolute scale. This course is an introduction to the field, with special emphasis on sound modern methods. The topics include knowledge representation, problem solving via search, game playing, logical and probabilistic reasoning, planning, dynamic programming, and reinforcement learning. Programming exercises concretize the key methods. The course targets graduate students and advanced undergraduates. Evaluation is based on written and programming assignments, a midterm and a final. Prerequisites: CSE 347, ESE 326, Math 233
CSE 514A: Data Mining T, R
Hillman 60 With the vast advancement in science and technology, data acquisition in large quantities are routinely done in many fields. Examples of large data include various types of data on the internet, high-throughput sequencing data in biology and medicine, extraterrestrial data from telescopes in astronomy, and images from surveillance camera in security. Mining a large amount of data through data mining has become an effective means to extracting knowledge from data. This course introduces the basic concepts and methods for data mining and provides hands-on experience for processing, analyzing and modeling structured and unstructured data. Homework problems, examines and programming assignments will be administrated throughout the course to enhance the learning. Prerequisites: CSE 247 and ESE 326 (or Math 320) or their equivalent, or permission of the instructor.
CSE 543T: Algorithms for Nonlinear Optimization T, R
Crow 204 The course will provide an in-depth coverage of modern algorithms for the numerical solution of multidimensional optimization problems. Unconstrained optimization techniques including Gradient methods, Newton’s methods, Quasi-Newton methods, and conjugate methods will be introduced. The emphasis is on constrained optimization techniques: Lagrange theory, Lagrangian methods, penalty methods, sequential quadratic programming, primal-dual methods, duality theory, nondifferentiable dual methods, and decomposition methods. The course will also discuss applications in engineering systems and use of state-of-the-art computer codes. Special topics may include large-scale systems, parallel optimization, and convex optimization. Prerequisites: Calculus I and Math 309
CSE 559A: Computer Vision T, R
Lopata 101 This course introduces the fundamentals of designing computer vision systems: that can “look at” images and videos and reason about the physical objects and scenes they represent. We will learn about methods for image restoration and enhancement; for estimating color, shape, geometry, and motion from images; and for image segmentation, recognition, and classification. The focus of the course will be on the mathematical tools and intuition underlying these methods: models for the physics and geometry of image formation, and statistical and machine learning-based techniques for inference. Prerequisites: CSE 247 and linear algebra.