Matches in SemOpenAlex for { <https://semopenalex.org/work/W2898813905> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2898813905 abstract "Deep Optimisation (DO) combines evolutionary search with Deep Neural Networks (DNNs) in a novel way - not for optimising a learning algorithm, but for finding a solution to an optimisation problem. Deep learning has been successfully applied to classification, regression, decision and generative tasks and in this paper we extend its application to solving optimisation problems. Model Building Optimisation Algorithms (MBOAs), a branch of evolutionary algorithms, have been successful in combining machine learning methods and evolutionary search but, until now, they have not utilised DNNs. DO is the first algorithm to use a DNN to learn and exploit the problem structure to adapt the variation operator (changing the neighbourhood structure of the search process). We demonstrate the performance of DO using two theoretical optimisation problems within the MAXSAT class. The Hierarchical Transformation Optimisation Problem (HTOP) has controllable deep structure that provides a clear evaluation of how DO works and why using a layerwise technique is essential for learning and exploiting problem structure. The Parity Modular Constraint Problem (MCparity) is a simplistic example of a problem containing higher-order dependencies (greater than pairwise) which DO can solve and state of the art MBOAs cannot. Further, we show that DO can exploit deep structure in TSP instances. Together these results show that there exists problems that DO can find and exploit deep problem structure that other algorithms cannot. Making this connection between DNNs and optimisation allows for the utilisation of advanced tools applicable to DNNs that current MBOAs are unable to use." @default.
- W2898813905 created "2018-11-09" @default.
- W2898813905 creator A5014510580 @default.
- W2898813905 creator A5016916851 @default.
- W2898813905 creator A5077710357 @default.
- W2898813905 creator A5082699760 @default.
- W2898813905 date "2018-11-02" @default.
- W2898813905 modified "2023-09-27" @default.
- W2898813905 title "Deep Optimisation: Solving Combinatorial Optimisation Problems using Deep Neural Networks." @default.
- W2898813905 cites W1482125571 @default.
- W2898813905 cites W1534872837 @default.
- W2898813905 cites W1559312966 @default.
- W2898813905 cites W1597286183 @default.
- W2898813905 cites W1597878669 @default.
- W2898813905 cites W1659842140 @default.
- W2898813905 cites W1944971855 @default.
- W2898813905 cites W1981734705 @default.
- W2898813905 cites W1997079881 @default.
- W2898813905 cites W2014644550 @default.
- W2898813905 cites W2017708378 @default.
- W2898813905 cites W2042492924 @default.
- W2898813905 cites W2056417590 @default.
- W2898813905 cites W2088928406 @default.
- W2898813905 cites W2100495367 @default.
- W2898813905 cites W2109694902 @default.
- W2898813905 cites W2111935653 @default.
- W2898813905 cites W2170086712 @default.
- W2898813905 cites W2734430578 @default.
- W2898813905 cites W2778749116 @default.
- W2898813905 cites W2950835015 @default.
- W2898813905 cites W2951430899 @default.
- W2898813905 cites W2952332632 @default.
- W2898813905 cites W3023540311 @default.
- W2898813905 hasPublicationYear "2018" @default.
- W2898813905 type Work @default.
- W2898813905 sameAs 2898813905 @default.
- W2898813905 citedByCount "3" @default.
- W2898813905 countsByYear W28988139052020 @default.
- W2898813905 crossrefType "posted-content" @default.
- W2898813905 hasAuthorship W2898813905A5014510580 @default.
- W2898813905 hasAuthorship W2898813905A5016916851 @default.
- W2898813905 hasAuthorship W2898813905A5077710357 @default.
- W2898813905 hasAuthorship W2898813905A5082699760 @default.
- W2898813905 hasConcept C108583219 @default.
- W2898813905 hasConcept C119857082 @default.
- W2898813905 hasConcept C126255220 @default.
- W2898813905 hasConcept C154945302 @default.
- W2898813905 hasConcept C159149176 @default.
- W2898813905 hasConcept C165696696 @default.
- W2898813905 hasConcept C184898388 @default.
- W2898813905 hasConcept C33923547 @default.
- W2898813905 hasConcept C38652104 @default.
- W2898813905 hasConcept C41008148 @default.
- W2898813905 hasConcept C50644808 @default.
- W2898813905 hasConceptScore W2898813905C108583219 @default.
- W2898813905 hasConceptScore W2898813905C119857082 @default.
- W2898813905 hasConceptScore W2898813905C126255220 @default.
- W2898813905 hasConceptScore W2898813905C154945302 @default.
- W2898813905 hasConceptScore W2898813905C159149176 @default.
- W2898813905 hasConceptScore W2898813905C165696696 @default.
- W2898813905 hasConceptScore W2898813905C184898388 @default.
- W2898813905 hasConceptScore W2898813905C33923547 @default.
- W2898813905 hasConceptScore W2898813905C38652104 @default.
- W2898813905 hasConceptScore W2898813905C41008148 @default.
- W2898813905 hasConceptScore W2898813905C50644808 @default.
- W2898813905 hasLocation W28988139051 @default.
- W2898813905 hasOpenAccess W2898813905 @default.
- W2898813905 hasPrimaryLocation W28988139051 @default.
- W2898813905 hasRelatedWork W1042791100 @default.
- W2898813905 hasRelatedWork W1543977710 @default.
- W2898813905 hasRelatedWork W1615495149 @default.
- W2898813905 hasRelatedWork W2279656496 @default.
- W2898813905 hasRelatedWork W2734430578 @default.
- W2898813905 hasRelatedWork W2762962669 @default.
- W2898813905 hasRelatedWork W2899166051 @default.
- W2898813905 hasRelatedWork W2972729876 @default.
- W2898813905 hasRelatedWork W3007468665 @default.
- W2898813905 hasRelatedWork W3017066206 @default.
- W2898813905 hasRelatedWork W3021685957 @default.
- W2898813905 hasRelatedWork W3045306759 @default.
- W2898813905 hasRelatedWork W3083758911 @default.
- W2898813905 hasRelatedWork W3161879230 @default.
- W2898813905 hasRelatedWork W3163083262 @default.
- W2898813905 hasRelatedWork W3181875459 @default.
- W2898813905 hasRelatedWork W3184011581 @default.
- W2898813905 hasRelatedWork W3209973822 @default.
- W2898813905 hasRelatedWork W3210763027 @default.
- W2898813905 hasRelatedWork W983390668 @default.
- W2898813905 isParatext "false" @default.
- W2898813905 isRetracted "false" @default.
- W2898813905 magId "2898813905" @default.
- W2898813905 workType "article" @default.