|
|
SGN-2806 NEURAL COMPUTATION, 5 cr
|
Person responsible
Prof. Ari Visa
Lecturers
Ari Visa, Professor, room TF309, ari.visa@tut.fi
Lecture room and time
Per III: Monday 10 - 12, TB215
Per III: Wednesday 14 - 16, TB215
Implementation rounds
Implementation 1
| Period 1 | Period 2 | Period 3 | Period 4 | Period 5 | Summer | Language of instruction | |
| Lecture | - | - | 4 h/week | - | - | - | In English only |
| Exercise | - | - | 2 h/week | - | - | - | In English only |
| Exam | In finnish and in english if asked | ||||||
Objectives
To give basic knowledge of neuro computing and to apply neuro computing to some application fields.
Contents
| Content | Core content | Complementary knowledge | Specialist knowledge |
| 1. | Learning processes | ||
| 2. | Learning machines with a teacher | Multilayer Perceptrons
Radial-Basis Function Networks Support Vector Machines Committee Machines |
|
| 3. | Learning machines without a teacher | Principal Component Analysis with Neural Networks
Self-Organizig Maps Boltzmann Machine |
|
| 4. | Nonlinear dynamical systems | Temporal Processing Using Feed Forward Network
Dynamically Driven Recurrent Network |
Requirements for completing the course
Final exam and attendance at the classroom exercises.
Assessment criteria
Exam and approx. 70% attendance at the exercises.
Study material
| Type | Name | Author | ISBN | URL, edition, availablitity... | Exam material | Language |
| Book | "Neural Networks: a Comprehensive Foundation" | Haykin, S. | 2nd edition, Prentice-Hall Inc, 1999 | Yes | English |
Prerequisites
| Number | Name | Credits | M/R |
| MAT-31090 | Matrix Algebra 1 | 5 | Recommendable |
| MAT-41120 | Optimization Theory 1 | 5 | Recommendable |
Other comments
The course is intended to students who are close to graduation in the fields of signal processing, computer science or telecommunication.
Lectures in English or in Finnish.
Correspondence of content
8001703 Neural Computation
| Last modified | 28.11.2005 |
| Modified by | Kirsi Järnström |