FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192267752> ?p ?o ?g. }

• W3192267752 abstract "Are deep convolutional neural networks (CNNs) for image classification explainable by utility maximization with information acquisition costs? We demonstrate that deep CNNs behave equivalently (in terms of necessary and sufficient conditions) to rationally inattentive utility maximizers, a generative model used extensively in economics for human decision making. Our claim is based by extensive experiments on 200 deep CNNs from 5 popular architectures. The parameters of our interpretable model are computed efficiently via convex feasibility algorithms. As an application, we show that our economics-based interpretable model can predict the classification performance of deep CNNs trained with arbitrary parameters with accuracy exceeding 94% . This eliminates the need to re-train the deep CNNs for image classification. The theoretical foundation of our approach lies in Bayesian revealed preference studied in micro-economics. All our results are on GitHub and completely reproducible." @default.
• W3192267752 created "2021-08-16" @default.
• W3192267752 creator A5068804090 @default.
• W3192267752 creator A5084702668 @default.
• W3192267752 date "2021-02-09" @default.
• W3192267752 modified "2023-09-24" @default.
• W3192267752 title "Rationally Inattentive Utility Maximization for Interpretable Deep Image Classification" @default.
• W3192267752 cites W1542183466 @default.
• W3192267752 cites W1588591676 @default.
• W3192267752 cites W1686810756 @default.
• W3192267752 cites W1787224781 @default.
• W3192267752 cites W1799366690 @default.
• W3192267752 cites W1972190631 @default.
• W3192267752 cites W2004394537 @default.
• W3192267752 cites W2025768430 @default.
• W3192267752 cites W2050495532 @default.
• W3192267752 cites W2072128103 @default.
• W3192267752 cites W2096577823 @default.
• W3192267752 cites W2117948809 @default.
• W3192267752 cites W2141125852 @default.
• W3192267752 cites W2153370118 @default.
• W3192267752 cites W2154579312 @default.
• W3192267752 cites W2163605009 @default.
• W3192267752 cites W2170126359 @default.
• W3192267752 cites W2171605416 @default.
• W3192267752 cites W2172039716 @default.
• W3192267752 cites W2194775991 @default.
• W3192267752 cites W2337034270 @default.
• W3192267752 cites W2346578521 @default.
• W3192267752 cites W2418098761 @default.
• W3192267752 cites W2420245003 @default.
• W3192267752 cites W2594475271 @default.
• W3192267752 cites W2962772482 @default.
• W3192267752 cites W2962851944 @default.
• W3192267752 cites W2962862931 @default.
• W3192267752 cites W2963058055 @default.
• W3192267752 cites W2963233086 @default.
• W3192267752 cites W2996367332 @default.
• W3192267752 cites W3002261956 @default.
• W3192267752 cites W3085907897 @default.
• W3192267752 cites W3118608800 @default.
• W3192267752 cites W3181191249 @default.
• W3192267752 cites W1522889714 @default.
• W3192267752 cites W3175086586 @default.
• W3192267752 hasPublicationYear "2021" @default.
• W3192267752 type Work @default.
• W3192267752 sameAs 3192267752 @default.
• W3192267752 citedByCount "0" @default.
• W3192267752 crossrefType "posted-content" @default.
• W3192267752 hasAuthorship W3192267752A5068804090 @default.
• W3192267752 hasAuthorship W3192267752A5084702668 @default.
• W3192267752 hasConcept C105795698 @default.
• W3192267752 hasConcept C107673813 @default.
• W3192267752 hasConcept C108583219 @default.
• W3192267752 hasConcept C115961682 @default.
• W3192267752 hasConcept C119857082 @default.
• W3192267752 hasConcept C126255220 @default.
• W3192267752 hasConcept C153180895 @default.
• W3192267752 hasConcept C154945302 @default.
• W3192267752 hasConcept C2776330181 @default.
• W3192267752 hasConcept C2778049539 @default.
• W3192267752 hasConcept C2781249084 @default.
• W3192267752 hasConcept C2984842247 @default.
• W3192267752 hasConcept C33923547 @default.
• W3192267752 hasConcept C41008148 @default.
• W3192267752 hasConcept C75294576 @default.
• W3192267752 hasConcept C81363708 @default.
• W3192267752 hasConceptScore W3192267752C105795698 @default.
• W3192267752 hasConceptScore W3192267752C107673813 @default.
• W3192267752 hasConceptScore W3192267752C108583219 @default.
• W3192267752 hasConceptScore W3192267752C115961682 @default.
• W3192267752 hasConceptScore W3192267752C119857082 @default.
• W3192267752 hasConceptScore W3192267752C126255220 @default.
• W3192267752 hasConceptScore W3192267752C153180895 @default.
• W3192267752 hasConceptScore W3192267752C154945302 @default.
• W3192267752 hasConceptScore W3192267752C2776330181 @default.
• W3192267752 hasConceptScore W3192267752C2778049539 @default.
• W3192267752 hasConceptScore W3192267752C2781249084 @default.
• W3192267752 hasConceptScore W3192267752C2984842247 @default.
• W3192267752 hasConceptScore W3192267752C33923547 @default.
• W3192267752 hasConceptScore W3192267752C41008148 @default.
• W3192267752 hasConceptScore W3192267752C75294576 @default.
• W3192267752 hasConceptScore W3192267752C81363708 @default.
• W3192267752 hasLocation W31922677521 @default.
• W3192267752 hasOpenAccess W3192267752 @default.
• W3192267752 hasPrimaryLocation W31922677521 @default.
• W3192267752 hasRelatedWork W1992699959 @default.
• W3192267752 hasRelatedWork W2029305120 @default.
• W3192267752 hasRelatedWork W2293361676 @default.
• W3192267752 hasRelatedWork W2553079770 @default.
• W3192267752 hasRelatedWork W2802511791 @default.
• W3192267752 hasRelatedWork W2803390034 @default.
• W3192267752 hasRelatedWork W2805054782 @default.
• W3192267752 hasRelatedWork W2889855722 @default.
• W3192267752 hasRelatedWork W2952775587 @default.
• W3192267752 hasRelatedWork W3000610597 @default.
• W3192267752 hasRelatedWork W3006654992 @default.
• W3192267752 hasRelatedWork W3010937527 @default.
• W3192267752 hasRelatedWork W3021438896 @default.
• W3192267752 hasRelatedWork W3048757909 @default.

• next