boulisDetailedTransc.. - University of Washington

tripastroturfAI and Robotics

Nov 7, 2013 (3 years and 5 months ago)

56 views

Constantinos Boulis boulis@ssli.ee.washington.edu

D
ETAILED
G
RADUATE
C
OURSES
T
RANSCRIPT



Since I believe that the titles that appear in the University of Washington transcript are not very
descriptive, I would like to take some extra space and present a very short description of the graduate
courses I reg
istered for. The description is the syllabus provided by the instructor.


Original Title

Short description

Grade

EE505 PROB & RAND PROCESSES

Foundations for the engineering analysis of random
processes: set theoretic fundamentals, basic axioms of
probabil
ity models, conditional probabilities and
independence, discrete and continuous random
variables, multiple random variables, sequences of
random variables, limit theorems, models of stochastic
processes, noise, stationarity and ergodicity, Gaussian
process
es, power spectral densities.

4.0

EE518 DGTL SIGNAL PROCESS

Digital representation of analog signals. Frequency
domain and Z
-
transforms of digital signals and systems
design of digital systems; IIR and FIR filter design
techniques, fast Fourier transform
algorithms. Sources
of error in digital systems. Analysis of noise in digital
systems.

3.4

EE516 COMP SPEECH PROC

Introduction to automatic speech processing. Overview
of human speech production and perception.
Fundamental theory in speech coding, synthes
is and
reproduction, as well as system design methodologies.
Advanced topics include speaker and language
identification and adaptation.

3.8

EE586 DIG VID COD SYS

Introduction to digital video coding algorithms,
standards, and systems.

Theoretical and pr
actical
aspects of important topics on digital video coding
algorithms, motion estimation, video coding standards,
systems and implementation issues, and visual
communications.

3.5

EE506 COMM THRY I

Review of stochastic processes. Communication
system mod
els. Channel noise and capacity. Optimum
detection, modulation and coding, convolutional coders
and decoders. Typical channels, random and fading
channels. Waveform communication, optimum filters.

3.8

EE566 COMP
-
COMM NETS II

Local area, metropolitan area,

satellite, and packet
radio networks; routing algorithms for wide area
networks; optimal design of packet
-
switched networks;
congestion and flow control; fast packet switching;
gigabit networks

4.0

INDE599 SPECIAL TOPICS IE

Modeling and analysis of rando
m processes
encountered in engineering applications. Stationarity
and ergodicity. Harmonic analysis, power spectral
densities. Karhunen
-
Loeve expansions. Poisson,
Gaussian, and Markov processes.

4.0

AA581 DIGITAL CONTROL I

Discrete
-
time and sampled
-
data s
ystems, the Z
-
transform, frequency domain properties; sampling, D/A
and A/D conversion issues; controller design via
discrete
-
time equivalents to continuous
-
time
controllers, by direct
-
digital root locus, by loop
shaping, and via state feedback and observe
rs.

3.4

Constantinos Boulis boulis@ssli.ee.washington.edu

EE596A ADV TOPICS S&I PROC

Covers classification and estimation of vector
observations, including both parametric and
nonparametric approaches. Includes classification with
likelihood functions and general discriminant
functions, density estimatio
n, supervised and
unsupervised learning, feature reduction, model
selection, and performance estimation.

4.0

EE596B ADV TOPICS S&I PROC

Bayesian networks, Markov random fields, factor
graphs, Markov properties, standard models as
graphical models, graph t
heory (e.g., moralization and
triangulation), probabilistic inference (including pearl's
belief propagation, Hugin, and Shafer
-
Shenoy),
junction threes, dynamic Bayesian networks (including
hidden Markov models), learning new models, models
in practice.

4.
0

MEDED598 SPC TPC IN INFOR

Introduction to computational linguistics and natural
language processing. Context
-
free grammars, natural
language parsing, morphology, pragmatics, lexical and
discourse semantics. Applications of NLP to
information retrieval a
nd text mining.

3.8

CSE590 SPEC TPCS COMP SCI

Computational Biology seminar with final project.

CR

EE520 SPTCR ANLYS TME SER

Estimation of spectral densities for single and multiple
time series. Nonparametric estimation of spectral
density, cross
-
spectr
al density, and coherency for
stationary time series, real and complex spectrum
techniques. Bispectrum. Digital filtering techniques.
Aliasing, prewhitening. Choice of lag windows and
data windows. Use of the fast Fourier transform. The
parametric autoregr
essive spectral density estimate for
single and multiple stationary time series. Spectral
analysis of nonstationary random processes and for
randomly sampled processes. Techniques of robust
spectral analysis.

3.9

CSE590 SPEC TPCS COMP SCI

Bayesian network
s, Markov networks, Markov chain
Monte Carlo, Belief propagation, Mixture models,
Maximum likelihood and Bayesian estimation, the EM
algorithm, Hidden Markov models, Dynamic Bayesian
networks, Particle filters

3.7



For the CSE590 SPEC TPCS COMP SCI there

was no Grade since the Credit/No Credit policy was opted
for. CR stands for Credit.


The EE596A ADV TOPICS S&I PROC course has been renamed to “Introduction to Statistical Learning “.
In Winter 2004, I served as the course’s grader.


The EE596B ADV TOPI
CS S&I PROC has been renamed to “Graphical Models in Pattern Recognition”.


In Spring 2005, I served as the grader for the graduate course EE 517 “Statistical Language Processing”.