FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132655441> ?p ?o ?g. }

• W3132655441 abstract "Abstract Basic oxygen steel making is a complex chemical and physical industrial process that reduces a mix of pig iron and recycled scrap into low-carbon steel. Good understanding of the process and the ability to predict how it will evolve requires long operator experience, but this can be augmented with process target prediction systems. Such systems may use machine learning to learn a model of the process based on a long process history, and have an advantage in that they can make use of vastly more process parameters than operators can comprehend. While it has become less of a challenge to build such prediction systems using machine learning algorithms, actual production implementations are rare. The hidden reasoning of complex prediction model and lack of transparency prevents operator trust, even for models that show high accuracy predictions. To express model behaviour and thereby increasing transparency we develop a reinforcement learning (RL) based agent approach, which task is to generate short polynomials that can explain the model of the process from what it has learnt from process data. The RL agent is rewarded on how well it generates polynomials that can predict the process from a smaller subset of the process parameters. Agent training is done with the REINFORCE algorithm, which enables the sampling of multiple concurrently plausible polynomials. Having multiple polynomials, process developers can evaluate several alternative and plausible explanations, as observed in the historic process data. The presented approach gives both a trained generative model and a set of polynomials that can explain the process. The performance of the polynomials is as good as or better than more complex and less interpretable models. Further, the relative simplicity of the resulting polynomials allows good generalisation to fit new instances of data. The best of the resulting polynomials in our evaluation achieves a better $$R^2$$ <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML><mml:msup><mml:mi>R</mml:mi><mml:mn>2</mml:mn></mml:msup></mml:math> score on the test set in comparison to the other machine learning models evaluated." @default.
• W3132655441 created "2021-03-01" @default.
• W3132655441 creator A5040314070 @default.
• W3132655441 creator A5049537875 @default.
• W3132655441 creator A5060132050 @default.
• W3132655441 date "2021-02-19" @default.
• W3132655441 modified "2023-10-14" @default.
• W3132655441 title "Using Reinforcement Learning for Generating Polynomial Models to Explain Complex Data" @default.
• W3132655441 cites W1975777241 @default.
• W3132655441 cites W1995806857 @default.
• W3132655441 cites W2007431958 @default.
• W3132655441 cites W2042702253 @default.
• W3132655441 cites W2058371505 @default.
• W3132655441 cites W2104764403 @default.
• W3132655441 cites W2125459357 @default.
• W3132655441 cites W2257979135 @default.
• W3132655441 cites W2282821441 @default.
• W3132655441 cites W2610148085 @default.
• W3132655441 cites W2759903677 @default.
• W3132655441 cites W2897072487 @default.
• W3132655441 cites W2938632598 @default.
• W3132655441 cites W2964081807 @default.
• W3132655441 cites W2964268978 @default.
• W3132655441 cites W3030915226 @default.
• W3132655441 doi "https://doi.org/10.1007/s42979-021-00488-w" @default.
• W3132655441 hasPublicationYear "2021" @default.
• W3132655441 type Work @default.
• W3132655441 sameAs 3132655441 @default.
• W3132655441 citedByCount "1" @default.
• W3132655441 countsByYear W31326554412022 @default.
• W3132655441 crossrefType "journal-article" @default.
• W3132655441 hasAuthorship W3132655441A5040314070 @default.
• W3132655441 hasAuthorship W3132655441A5049537875 @default.
• W3132655441 hasAuthorship W3132655441A5060132050 @default.
• W3132655441 hasBestOaLocation W31326554411 @default.
• W3132655441 hasConcept C104317684 @default.
• W3132655441 hasConcept C111919701 @default.
• W3132655441 hasConcept C119857082 @default.
• W3132655441 hasConcept C154945302 @default.
• W3132655441 hasConcept C158448853 @default.
• W3132655441 hasConcept C17020691 @default.
• W3132655441 hasConcept C177264268 @default.
• W3132655441 hasConcept C185592680 @default.
• W3132655441 hasConcept C199360897 @default.
• W3132655441 hasConcept C2780233690 @default.
• W3132655441 hasConcept C38652104 @default.
• W3132655441 hasConcept C41008148 @default.
• W3132655441 hasConcept C55493867 @default.
• W3132655441 hasConcept C86339819 @default.
• W3132655441 hasConcept C97541855 @default.
• W3132655441 hasConcept C98045186 @default.
• W3132655441 hasConceptScore W3132655441C104317684 @default.
• W3132655441 hasConceptScore W3132655441C111919701 @default.
• W3132655441 hasConceptScore W3132655441C119857082 @default.
• W3132655441 hasConceptScore W3132655441C154945302 @default.
• W3132655441 hasConceptScore W3132655441C158448853 @default.
• W3132655441 hasConceptScore W3132655441C17020691 @default.
• W3132655441 hasConceptScore W3132655441C177264268 @default.
• W3132655441 hasConceptScore W3132655441C185592680 @default.
• W3132655441 hasConceptScore W3132655441C199360897 @default.
• W3132655441 hasConceptScore W3132655441C2780233690 @default.
• W3132655441 hasConceptScore W3132655441C38652104 @default.
• W3132655441 hasConceptScore W3132655441C41008148 @default.
• W3132655441 hasConceptScore W3132655441C55493867 @default.
• W3132655441 hasConceptScore W3132655441C86339819 @default.
• W3132655441 hasConceptScore W3132655441C97541855 @default.
• W3132655441 hasConceptScore W3132655441C98045186 @default.
• W3132655441 hasFunder F4320321759 @default.
• W3132655441 hasFunder F4320328657 @default.
• W3132655441 hasIssue "2" @default.
• W3132655441 hasLocation W31326554411 @default.
• W3132655441 hasLocation W31326554412 @default.
• W3132655441 hasOpenAccess W3132655441 @default.
• W3132655441 hasPrimaryLocation W31326554411 @default.
• W3132655441 hasRelatedWork W1562959674 @default.
• W3132655441 hasRelatedWork W2923653485 @default.
• W3132655441 hasRelatedWork W2957776456 @default.
• W3132655441 hasRelatedWork W3022038857 @default.
• W3132655441 hasRelatedWork W3088315509 @default.
• W3132655441 hasRelatedWork W3209094908 @default.
• W3132655441 hasRelatedWork W4210912933 @default.
• W3132655441 hasRelatedWork W4255994452 @default.
• W3132655441 hasRelatedWork W4319083788 @default.
• W3132655441 hasRelatedWork W4361026739 @default.
• W3132655441 hasVolume "2" @default.
• W3132655441 isParatext "false" @default.
• W3132655441 isRetracted "false" @default.
• W3132655441 magId "3132655441" @default.
• W3132655441 workType "article" @default.