The advantages of non-monotonic logic in modular architectures: High performance and interpretable outputs with limited training data

ResearchSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Sridharan, M en
dc.contributor.author Riley, Heather en
dc.date.accessioned 2019-07-03T23:55:34Z en
dc.date.issued 2019 en
dc.identifier.uri http://hdl.handle.net/2292/47325 en
dc.description Full Text is available to authenticated members of The University of Auckland only. en
dc.description.abstract Deep learning has become the state of the art algorithm for many areas of machine learning research. Deep learning can achieve high performance but it requires a lot of training data and is not readily interpretable.This makes it difficult to develop algorithms for new applications, as errors cannot easily be resolved when the algorithm’s reasoning is obscure, and large datasets cannot always be obtained. To address these limitations logic knowledge bases can be used for interpretable reasoning while deep learning is used used for any processing that is not suitable for representation by a knowledge base. A knowledge base requires no training data and provides interpretable outputs, and in addition, the intermediate outputs from knowledge base components can be used to guide learning for the deep learning components, making training more efficient. These advantages were central to the design of a novel architecture, which used deep learning for image processing and a combination of non-monotonic logic and decision tree induction for interpretable reasoning. Performance was evaluated with visual question answering (VQA), and a state of the art planning architecture was used to show the advantages of knowledge bases in dynamic domains. The VQA architecture’s performance was evaluated in two domains: estimating the stability of simulated block towers, and determining the messages conveyed by traffic signs. Experimental results showed that the proposed architecture achieved interpretability and high performance with small training datasets. The planning architecture was evaluated in a dynamic tower-building domain. Another domain in which a simulated Turtlebot acted as an office assistant was used to show that the VQA and planning architectures could be combined. The performance of knowledge base reasoning was improved through the use of automated axiom learning, which was shown in all four domains. In the stability and traffic domains the use of axiom learning to add to the knowledge base improved VQA accuracy, while in the tower building and office assistant domains the action plans developed after axiom learning were more sensible and efficient than those developed before. en
dc.publisher ResearchSpace@Auckland en
dc.relation.ispartof Masters Thesis - University of Auckland en
dc.relation.isreferencedby UoA99265162812902091 en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights Restricted Item. Full Text is available to authenticated members of The University of Auckland only. en
dc.rights.uri https://researchspace.auckland.ac.nz/docs/uoa-docs/rights.htm en
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/nz/ en
dc.title The advantages of non-monotonic logic in modular architectures: High performance and interpretable outputs with limited training data en
dc.type Thesis en
thesis.degree.discipline Computer systems engineering en
thesis.degree.grantor The University of Auckland en
thesis.degree.level Masters en
dc.rights.holder Copyright: The author en
pubs.elements-id 775989 en
pubs.record-created-at-source-date 2019-07-04 en


Full text options

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by-nc-sa/3.0/nz/ Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc-sa/3.0/nz/

Share

Search ResearchSpace


Advanced Search

Browse