Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Gaussian Processes: Designing Receivers

In course

COM-302: Principles of digital communications

This course is on the foundations of digital communication. The focus is on the transmission problem (rather than being on source coding). ...

Description

This lecture covers the theory behind Gaussian processes, the MAP rule, sufficiency, irrelevance, and the design of receivers using MAP calculations and maximum likelihood estimation.

Instructor

Emre Telatar

I. Emre Telatar received the B.Sc. degree in electrical engineering from the Middle East Technical University, Ankara, Turkey, in 1986. He received the S.M. and Ph.D. degrees in electrical engineering and computer science from the Massachusetts Institute of Technology, Cambridge, in 1988 and 1992 respectively. In 1992, he joined the Communications Analysis Research Department at AT&T Bell Laboratories (later Lucent Technologies), Murray Hill, NJ. He has been at the EPFL since 2000. Emre Telatar was the recipient of the IEEE Information Theory Society Paper Award in 2001. He was a program co-chair for the IEEE International Symposium on Information Theory in 2002, and associate editor for Shannon Theory for the IEEE Information Theory Transactions from 2001 to 2004. He was awarded the EPFL Agepoly teaching prize in 2005. Emre Telatar's research interests are in communication and information theories.

Official source

Related concepts (32)

Maximum likelihood estimation

In statistics, maximum likelihood estimation (MLE) is a method of estimating the parameters of an assumed probability distribution, given some observed data. This is achieved by maximizing a likelihood function so that, under the assumed statistical model, the observed data is most probable. The point in the parameter space that maximizes the likelihood function is called the maximum likelihood estimate. The logic of maximum likelihood is both intuitive and flexible, and as such the method has become a dominant means of statistical inference.

Statistical inference

Statistical inference is the process of using data analysis to infer properties of an underlying distribution of probability. Inferential statistical analysis infers properties of a population, for example by testing hypotheses and deriving estimates. It is assumed that the observed data set is sampled from a larger population. Inferential statistics can be contrasted with descriptive statistics. Descriptive statistics is solely concerned with properties of the observed data, and it does not rest on the assumption that the data come from a larger population.

Frequentist inference

Frequentist inference is a type of statistical inference based in frequentist probability, which treats “probability” in equivalent terms to “frequency” and draws conclusions from sample-data by means of emphasizing the frequency or proportion of findings in the data. Frequentist-inference underlies frequentist statistics, in which the well-established methodologies of statistical hypothesis testing and confidence intervals are founded. The primary formulation of frequentism stems from the presumption that statistics could be perceived to have been a probabilistic frequency.

Mars

Mars is the fourth planet and the furthest terrestrial planet from the Sun. The reddish color of its surface is due to finely grained iron(III) oxide dust in the soil, giving it the nickname "the Red Planet". Mars's radius is second smallest among the planets in the Solar System at . The Martian dichotomy is visible on the surface: on average, the terrain on Mars's northern hemisphere is flatter and lower than its southern hemisphere. Mars has a thin atmosphere made primarily of carbon dioxide and two irregularly shaped natural satellites: Phobos and Deimos.

Filter (signal processing)

In signal processing, a filter is a device or process that removes some unwanted components or features from a signal. Filtering is a class of signal processing, the defining feature of filters being the complete or partial suppression of some aspect of the signal. Most often, this means removing some frequencies or frequency bands. However, filters do not exclusively act in the frequency domain; especially in the field of many other targets for filtering exist.

Related lectures (44)

Probabilistic Models for Linear Regression

Covers the probabilistic model for linear regression and its applications in nuclear magnetic resonance and X-ray imaging.

Linear Regression: Statistical Inference Perspective

Explores linear regression from a statistical inference perspective, covering probabilistic models, ground truth, labels, and maximum likelihood estimators.

Signal Processing Fundamentals

Covers the alternate formulation of signal processing and the sufficiency of the Waliland ratio in signal sets.

Detection & Estimation

Covers the fundamentals of detection and estimation theory, focusing on mean-squared error and hypothesis testing.

EMG: figures propagation