Inlämning av Examensarbete / Submission of Thesis

Nedelko Grbic MEE 97-04, pp. 35. Dept. of Signal Processing, 1997.

The work

Författare / Author: Nedelko Grbic
Titel / Title: Development of a General Purpose On-Line Update Multiple Layer Feedforward Backpropagation Neural Network
Abstrakt Abstract:

This Master thesis deals with the complete understanding and creation of a 3-layer Backpropagation Neural Network with synaptic weight update performed on a per sample basis (called, On-Line update). The aim is to create such a network for general purpose applications and with a great degree of freedom in choosing the inner structure of the network. The algorithms used are all members of supervised learning classes, i.e. they are all supervised by a desired signal.

The theory will be treated thoroughly for the steepest descent algorithm and for additional features which can be employed in order to increase the degree of generalization and learning rate for the network.

Empirical results will be presented and some comparsions with pure linear algorithms will be made for a signal processing applications, speech enhencement.

Ämnesord / Subject: Signalbehandling - Signal Processing

Nyckelord / Keywords: Neural network

Publication info

Dokument id / Document id:
Program:/ Programme Magisterprogram i Elektroteknik / Master of Science in Electrical Engineering
Registreringsdatum / Date of registration: 10/20/2005
Uppsatstyp / Type of thesis: D-Uppsats/Magister/Master

Context

Handledare / Supervisor: Mattias Dahl
Organisation / Organisation: Blekinge Institute of Technology
Institution / School: Dept. of Signal Processing

+46 455 780 00

Files & Access

Bifogad uppsats fil(er) / Files attached: development of a general purpose....pdf (339 kB, öppnas i nytt fönster)