ASTRON 193 - Noise and Data Analysis in Astrophysics or return to Course Catalog Search
114603 – Section 001
|Faculty of Arts and Sciences||Astronomy||Aneta Siemiginowska and Vinay Kashyap|
|Term||Day and Time|
|Spring 2016-2017 (show academic calendar)||MW 2:00 p.m. - 3:29 p.m.|
4 (show credit conversion for other schools)
Credit in Faculty of Arts and Sciences is equivalent to:
Graduate and Undergraduate
How to design experiments and get the most information from noisy, incomplete, flawed, and biased data sets. Basic of Probability theory; Bernoulli trials: Bayes theorem; random variables; distributions; functions of random variables; moments and characteristic functions; Fourier transform analysis; Stochastic processes; estimation of power spectra: sampling theorem, filtering; fast Fourier transform; spectrum of quantized data sets. Weighted least mean squares analysis and nonlinear parameter estimation. Bootstrap methods. Noise processes in periodic phenomena. Image processing and restoration techniques. The course will emphasize a Bayesian approach to problem solving and the analysis of real data sets.
Prerequisite: Mathematics 21b
This course offered alternate years.
|Eligible for cross-registration|
With permission of instructor/subject to availability
MIT students please cross register from MIT's Add/Drop application.