M1107-CMS11
Machine Learning and Data Mining
|
|
Module Owner: |
N.N. |
Displayed in timetable as: |
CMS-COR-MLD |
Duration: |
3 |
Number of electives: |
0 |
Credits: |
5,0
|
Start Semester: |
WiSe 2018/19 |
Lecturer Responsible |
Prof. Dr. Ivo Sbalzarini
ivo.sbalzarini@tu-dresden.de
|
Qualification Goals |
Upon completing the module, students master the basics and handling of forward problems and inverse problems in computer-aided science. They intuitively comprehend the meaning and definition of these two problem formulations, as well as the relationship with generative and discriminative approaches in Statistics. They know the theoretical connections between these two formulations, as given by the Theorem of Bayes and the Euler-Lagrange equations. For forward problems, students know what verification and validation mean, and can apply these in practice. For inverse problems, students are familiar with the basics of machine learning, in particular supervised and unsupervised approaches, as well as the concepts of overfitting and cross validation. |
Content |
Mathematical formulation of forward problems and inverse problems, generative and discriminative modelling approaches, Bayes theorem, Euler-Lagrange equations of optimisation, verification and validation of models and simulations, basics of machine learning, supervised learning, unsupervised learning, overfitting, cross validation, learning as an optimisation problem, basics of neural networks. |
Forms of Teaching and Learning |
The module includes 2 SWS worth of lectures, 2 SWS worth of exercises and the self-study. |
Prerequisites for Participation |
Knowledge in sequential computer programming, algorithms and data structures, analysis of functions of one and several variables, linear algebra (vector and matrix calculation), as well as probability calculation and Statistics at the Bachelor's level is required.
With the following literature, students can prepare for the module:
Harel: Algorithmics - The Spirit of Computing, Addison-Wesley, 2004
Schildt: C ++ from the ground up, McGraw-Hill, 2003
Abelson, Hal; Sussman, Gerald Jay: Structure and Interpretation of Computer Programs. MIT Press, 1985;
Cormen, Leiserson, Rivest & Stein: Introduction to Algorithms, 2nd Edition, MIT Press 2001;
Lax, Terrell: Multivariable Calculus with Applications (Undergraduate Texts in Mathematics), Springer, 2018
Hefferon, Jim: Linear Algebra, http://joshua.smcvt.edu/linearalgebra/, 2008. |
Applicability |
In the Computational Modelling and Simulation Master's programme, the module is one of six compulsory elective modules (for students of Computational Life Science: five), of which three must be chosen. This module fulfils the prerequisites for the CMS-EE-SCEE and CMS-EE-REEP modules. |
Prerequisites for the Assignment of Credit Points |
The credit points are awarded if the module examination is passed. If there are more than 10 registered students, the module examination consists of a written examination, with a duration of 90 minutes. If there are 10 or fewer registered students, it consists of an oral examination as an individual examination performance amounting to 30 minutes; this will be announced to the enrolled students at the end of the enrollment period. |
Credit Points and Grades |
This module allows for the earning of 5 credit points. The module grade corresponds to the grade of the examination performance. |
Frequency of Offer |
The module is offered each year during the winter semester. |
Workload |
The workload is a total of 150 hours. |
Duration of Module |
The module takes one semester. |
Module Number Module Handbook TU Dresden |
CMS-COR-MLD |