Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Inductive machine learning bias in knowledge-based neurocomputing
Thesis (MSc) -- Stellenbosch University , 2003.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2012
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614085983502336 |
|---|---|
| access_status_str | Open Access |
| author | Snyders, Sean |
| author2 | Omlin, Christian W. |
| author_browse | Omlin, Christian W. Snyders, Sean |
| author_facet | Omlin, Christian W. Snyders, Sean |
| author_sort | Snyders, Sean |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MSc) -- Stellenbosch University , 2003. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/53463 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:46:25.318Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2012 |
| publishDateRange | 2012 |
| publishDateSort | 2012 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/53463 Inductive machine learning bias in knowledge-based neurocomputing Snyders, Sean Omlin, Christian W. Stellenbosch University. Faculty of Science. Dept. of Mathematical Scineces. Neural computers Neural networks (Computer science) Artificial intelligence -- Data processing Knowledge-based neurocomputing Dissertations -- Computer science Dissertations -- Mathematical sciences Theses -- Mathematical sciences Dissertations -- Computer science Theses -- Computer science Thesis (MSc) -- Stellenbosch University , 2003. ENGLISH ABSTRACT: The integration of symbolic knowledge with artificial neural networks is becoming an increasingly popular paradigm for solving real-world problems. This paradigm named knowledge-based neurocomputing, provides means for using prior knowledge to determine the network architecture, to program a subset of weights to induce a learning bias which guides network training, and to extract refined knowledge from trained neural networks. The role of neural networks then becomes that of knowledge refinement. It thus provides a methodology for dealing with uncertainty in the initial domain theory. In this thesis, we address several advantages of this paradigm and propose a solution for the open question of determining the strength of this learning, or inductive, bias. We develop a heuristic for determining the strength of the inductive bias that takes the network architecture, the prior knowledge, the learning method, and the training data into consideration. We apply this heuristic to well-known synthetic problems as well as published difficult real-world problems in the domain of molecular biology and medical diagnoses. We found that, not only do the networks trained with this adaptive inductive bias show superior performance over networks trained with the standard method of determining the strength of the inductive bias, but that the extracted refined knowledge from these trained networks deliver more concise and accurate domain theories. AFRIKAANSE OPSOMMING: Die integrasie van simboliese kennis met kunsmatige neurale netwerke word 'n toenemende gewilde paradigma om reelewereldse probleme op te los. Hierdie paradigma genoem, kennis-gebaseerde neurokomputasie, verskaf die vermoe om vooraf kennis te gebruik om die netwerkargitektuur te bepaal, om a subversameling van gewigte te programeer om 'n leersydigheid te induseer wat netwerkopleiding lei, en om verfynde kennis van geleerde netwerke te kan ontsluit. Die rol van neurale netwerke word dan die van kennisverfyning. Dit verskaf dus 'n metodologie vir die behandeling van onsekerheid in die aanvangsdomeinteorie. In hierdie tesis adresseer ons verskeie voordele wat bevat is in hierdie paradigma en stel ons 'n oplossing voor vir die oop vraag om die gewig van hierdie leer-, of induktiewe sydigheid te bepaal. Ons ontwikkel 'n heuristiek vir die bepaling van die induktiewe sydigheid wat die netwerkargitektuur, die aanvangskennis, die leermetode, en die data vir die leer proses in ag neem. Ons pas hierdie heuristiek toe op bekende sintetiese probleme so weI as op gepubliseerde moeilike reelewereldse probleme in die gebied van molekulere biologie en mediese diagnostiek. Ons bevind dat, nie alleenlik vertoon die netwerke wat geleer is met die adaptiewe induktiewe sydigheid superieure verrigting bo die netwerke wat geleer is met die standaardmetode om die gewig van die induktiewe sydigheid te bepaal nie, maar ook dat die verfynde kennis wat ontsluit is uit hierdie geleerde netwerke meer bondige en akkurate domeinteorie lewer. 2012-08-27T11:35:29Z 2012-08-27T11:35:29Z 2003-04 Thesis http://hdl.handle.net/10019.1/53463 en_ZA Stellenbosch University 89 p. : ill. application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Neural computers Neural networks (Computer science) Artificial intelligence -- Data processing Knowledge-based neurocomputing Dissertations -- Computer science Dissertations -- Mathematical sciences Theses -- Mathematical sciences Dissertations -- Computer science Theses -- Computer science Snyders, Sean Inductive machine learning bias in knowledge-based neurocomputing |
| title | Inductive machine learning bias in knowledge-based neurocomputing |
| title_full | Inductive machine learning bias in knowledge-based neurocomputing |
| title_fullStr | Inductive machine learning bias in knowledge-based neurocomputing |
| title_full_unstemmed | Inductive machine learning bias in knowledge-based neurocomputing |
| title_short | Inductive machine learning bias in knowledge-based neurocomputing |
| title_sort | inductive machine learning bias in knowledge based neurocomputing |
| topic | Neural computers Neural networks (Computer science) Artificial intelligence -- Data processing Knowledge-based neurocomputing Dissertations -- Computer science Dissertations -- Mathematical sciences Theses -- Mathematical sciences Dissertations -- Computer science Theses -- Computer science |
| url | http://hdl.handle.net/10019.1/53463 |
| work_keys_str_mv | AT snyderssean inductivemachinelearningbiasinknowledgebasedneurocomputing |