|
|
|
|
|
|
|
Course Criteria
Add courses to your favorites to save, share, and find your best transfer school.
-
1.00 Credits
This course addresses the problem of modeling the perceptual neocortex using probabilistic graphical models, including Bayesian and Markov networks, and extensions to model time and change such as hidden Markov models and dynamic Bayesian networks. The emphasis is on problems of learning, inference, and attention. Sources include the literature in computational and cognitive neuroscience, machine learning, and other fields that bear on how biological and engineered systems make sense of the world. Prerequisites: basic probability theory, algorithms and statistics.
-
1.00 Credits
In this graduate seminar we will learn about models of human cognition and perception, and explore potential implications of the models on how computers and humans can interact effectively when performing scientific analyses. Participants will be responsible for reading assigned materials, taking turns guiding discussions of the readings, and preparing a final paper and presentation. It is recommended that participants have some background in at least one of the areas of study.
-
1.00 Credits
Every year will cover a different topic in computational linguistics, from a statistical point of view, including parsing, machine translation, conference, summarization, etc. Prerequisites: COGS 1360 or CSCI 1460, or permission of the instructor.
-
1.00 Credits
Devoted to computational problems and methods in the emerging field of Medical Bioinformatics where genomics, computational biology and bioinformatics impact medical research. We will present challenging problems and solutions in three areas: Disease Associations, Protein Folding and Immunogenomics. This course is open to graduate students and advanced undergraduates with Computational or Life Science backgrounds. Prior background in Biology is not required.
-
1.00 Credits
Course investigates the interplay of economic theory and computer science. It is suitable for advanced senior undergraduates and for graduate students. We will study topics such as: algorithms for selfish routing; competitive combinatorial auctions; Multicast cost sharing and cooperative games; graphical models for games; and related topics. This course will be organized around the presentation of recent research papers. Prerequisites: CS 157 or equivalent.
-
1.00 Credits
No description available.
-
1.00 Credits
Introduces the mathematical and computational foundations of brain-computer interfaces. Statistical learning, Bayesian inference, dimensionality reduction, information theory, and other topics are presented in the context of brain interfaces based on neural implants and EEG recordings. Prerequisites: Basic knowledge of probability, statistics and linear algebra (e.g., CS 155, AM 40, AM 165, AM 169, or AM 264). Enrollment limited to 20 students.
-
1.00 Credits
This seminar course explores current research topics in statistical machine learning. Focus varies by year, and may include Bayesian nonparametrics; models for spatial, temporal, or structured data; and variational or Monte Carlo approximations. Course meetings combine lectures with presentation and discussion of classical and contemporary research papers. Students will apply some this material to a project, ideally drawn from their own research interests.
-
1.00 Credits
This course will cover current topics in computer vision by focusing on a single real problem in computer vision. Recent courses have focused on forensic video analysis of an unsolved murder and three-dimensional object recognition for a mobile robot. Readings from the literature are integrated with group projects to solve problems beyond the state of the art. Strong mathematical skills (probability, linear algebra, calculus) and previous exposure to computer vision (e.g. CSCI 1430) are essential.
-
1.00 Credits
Planar graphs arise in applications such as road map navigation and logistics, graph drawing, and image processing. We will study graph algorithms and data structures that exploit planarity. Our focus will be on recent research results in optimization. Prerequisite: CSCI 1570 or the equivalent.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Privacy Statement
|
Terms of Use
|
Institutional Membership Information
|
About AcademyOne
Copyright 2006 - 2025 AcademyOne, Inc.
|
|
|