First cycle
degree courses
Second cycle
degree courses
Single cycle
degree courses
School of Engineering
MATHEMATICAL ENGINEERING
Course unit
SYSTEM IDENTIFICATION AND DATA ANALYSIS
INP8084399, A.A. 2019/20

Information concerning the students who enrolled in A.Y. 2019/20

Information on the course unit
Degree course Second cycle degree in
MATHEMATICAL ENGINEERING
IN2191, Degree course structure A.Y. 2017/18, A.Y. 2019/20
N0
bring this page
with you
Degree course track Common track
Number of ECTS credits allocated 9.0
Type of assessment Mark
Course unit English denomination SYSTEM IDENTIFICATION AND DATA ANALYSIS
Department of reference Department of Civil, Environmental and Architectural Engineering
Mandatory attendance No
Language of instruction English
Branch PADOVA
Single Course unit The Course unit can be attended under the option Single Course unit attendance
Optional Course unit The Course unit can be chosen as Optional Course unit

Lecturers
Teacher in charge GIORGIO PICCI 000000000000

ECTS: details
Type Scientific-Disciplinary Sector Credits allocated
Core courses ING-INF/04 Automatics 9.0

Course unit organization
Period Second semester
Year 1st Year
Teaching method frontal

Type of hours Credits Teaching
hours
Hours of
Individual study
Shifts
Lecture 9.0 72 153.0 No turn

Calendar
Start of activities 02/03/2020
End of activities 12/06/2020
Show course schedule 2019/20 Reg.2017 course timetable

Examination board
Board From To Members of the board
1 208 01/10/2018 15/03/2020 PICCI GIORGIO (Presidente)
CALLEGARO GIORGIA (Membro Effettivo)
PINZONI STEFANO (Supplente)

Syllabus
Prerequisites: None
Target skills and knowledge: Objective
Introduce the students to statistical learning methods for mathematical model building from experimental data

Outcomes
A student who has met the objectives of the course should have acquired a fundamental knowledge of modern statistical learning methods and of the numerical algorithms for model estimation and model-based prediction and decision making. Should acquire a basic understanding of deterministic and stochastic methods for time series and dynamical model identification
Examination methods: Written with optional computer project. Two Partial tests during the academic year plus four regular exam sessions
Assessment criteria: Completeness and orderliness of essay; clarity of exposition; rigour in using the technical terminology. The level of correspondence to these criteria will determine the graduation of the judgement and, consequently, the final mark.
Course unit contents: 1. Review of classical Statistical theory;
2. Linear models estimation: Maximum Likelihood, vector and matrix least squares problems
3. Conditioning and regularization. Ridge regression, the Lasso and related algorithms. Basic Spline regression.
4. Linear Hypotheses and Linear Discriminant Analysis. Pattern recognition, the Perceptron and the basic ideas of Support Vector Machines
5. Bayesian Statistics, MAP and minimum variance estimation. The Hilbert space setting.
6. Principal Components Analysis (PCA), data compression and applications to recognition and classification problems. The continuous parameter case: Reproducing Kernels.
7. Non linear Inference: Neural Networks and logistic regression
8. Basics on stationary random processes. Modeling and identification of Time Series; parameter estimation of ARX models and their asymptotic behaviour. The problem of order selection.
9. Recursive identification algorithms. Kalman filter like algorithms.
Planned learning activities and teaching methods: Frontal teaching and practical exercises, that the student has to further develop and deepen with his study.
Additional notes about suggested reading: Classroom notes: STATISTICAL METHODS FOR DYNAMICAL DATA ANALYSIS by Giorgio Picci
Textbooks (and optional supplementary readings)
  • Hastie Tibshirani Friedman, The Elements of Statistical Learning. --: Springer, 2009. Cerca nel catalogo