Module Handbook

  • Dynamischer Default-Fachbereich geändert auf MAT

Module MAT-80-13A-M-4

Introduction to Neural Networks (M, 4.5 LP)

Module Identification

Module Number Module Name CP (Effort)
MAT-80-13A-M-4 Introduction to Neural Networks 4.5 CP (135 h)

Basedata

CP, Effort 4.5 CP = 135 h
Position of the semester 1 Sem. irreg.
Level [4] Bachelor (Specialization)
Language [EN] English
Module Manager
Lecturers
Area of study [MAT-TEMA] Industrial Mathematics
Reference course of study [MAT-88.105-SG] M.Sc. Mathematics
Livecycle-State [NORM] Active

Notice

Without a proof of successful participation in the exercise classes, only 3 credit points will be awarded for the module.

Courses

Type/SWS Course Number Title Choice in
Module-Part
Presence-Time /
Self-Study
SL SL is
required for exa.
PL CP Sem.
2V+1U MAT-80-13A-K-4
Introduction to Neural Networks
P 42 h 93 h
U-Schein
- PL1 4.5 irreg.
  • About [MAT-80-13A-K-4]: Title: "Introduction to Neural Networks"; Presence-Time: 42 h; Self-Study: 93 h
  • About [MAT-80-13A-K-4]: The study achievement "[U-Schein] proof of successful participation in the exercise classes (ungraded)" must be obtained.

Examination achievement PL1

  • Form of examination: oral examination (20-30 Min.)
  • Examination Frequency: irregular (by arrangement)
  • Examination number: 84280 ("Introduction to Neural Networks")

Evaluation of grades

The grade of the module examination is also the module grade.


Contents

Basic terms and ideas of the theory of neural networks as well as their applications are discussed. In particular, the following contents will be covered:
  • easy perceptrons, multi-(hidden-)layer-perceptrons,
  • propositions about separation and classification,
  • basics of supervised and unsupervised learning.

Competencies / intended learning achievements

Upon completion of this module, the students have studied and understand the basic concepts required for describing neural networks and the mathematical techniques needed for analyzing these networks. They are familiarized with the various possibilities as to where different types of networks can be applied. They understand the proofs presented in the lecture and are able to comprehend and explain them.

By completing the given exercises, the students have developed a skilled, precise and independent handling of the terms, propositions and techniques taught in the lecture. In addition, they have learnt how to apply these techniques to new problems, analyze them and develop solution strategies independently or by team work.

Literature

  • S. Haykin: Neural Networks and Learning Machines: A Comprehensive Foundation,
  • M.T. Hagan, H.B. Demuth, M. Beale: Neural Network Design,
  • M.L. Minsky, S.A. Papert: Perceptrons.

Registration

Registration for the exercise classes via the online administration system URM (https://urm.mathematik.uni-kl.de).

Requirements for attendance of the module (informal)

Modules:

Courses

Requirements for attendance of the module (formal)

None

References to Module / Module Number [MAT-80-13A-M-4]

Course of Study Section Choice/Obligation
[MAT-88.105-SG] M.Sc. Mathematics [Core Modules (non specialised)] Applied Mathematics [WP] Compulsory Elective
[MAT-88.118-SG] M.Sc. Industrial Mathematics [Core Modules (non specialised)] General Mathematics [WP] Compulsory Elective
[MAT-88.276-SG] M.Sc. Business Mathematics [Core Modules (non specialised)] General Mathematics [WP] Compulsory Elective
[MAT-88.706-SG] M.Sc. Mathematics International [Core Modules (non specialised)] Applied Mathematics [WP] Compulsory Elective
[MAT-88.B84-SG] M.Sc. Actuarial and Financial Mathematics [Core Modules (non specialised)] Statistics and Computational Methods [WP] Compulsory Elective