Matches in SemOpenAlex for { <https://semopenalex.org/work/W3039697905> ?p ?o ?g. }
- W3039697905 abstract "We study the problem of learning efficient algorithms that strongly generalize in the framework of neural program induction. By carefully designing the input / output interfaces of the neural model and through imitation, we are able to learn models that produce correct results for arbitrary input sizes, achieving strong generalization. Moreover, by using reinforcement learning, we optimize for program efficiency metrics, and discover new algorithms that surpass the teacher used in imitation. With this, our approach can learn to outperform custom-written solutions for a variety of problems, as we tested it on sorting, searching in ordered lists and the NP-complete 0/1 knapsack problem, which sets a notable milestone in the field of Neural Program Induction. As highlights, our learned model can perform sorting perfectly on any input data size we tested on, with $O(n log n)$ complexity, whilst outperforming hand-coded algorithms, including quick sort, in number of operations even for list sizes far beyond those seen during training." @default.
- W3039697905 created "2020-07-10" @default.
- W3039697905 creator A5000173050 @default.
- W3039697905 creator A5003562101 @default.
- W3039697905 creator A5013834379 @default.
- W3039697905 creator A5039679910 @default.
- W3039697905 date "2020-07-07" @default.
- W3039697905 modified "2023-09-27" @default.
- W3039697905 title "Strong Generalization and Efficiency in Neural Programs" @default.
- W3039697905 cites W1732222442 @default.
- W3039697905 cites W1777239053 @default.
- W3039697905 cites W1982370770 @default.
- W3039697905 cites W2114012357 @default.
- W3039697905 cites W2121863487 @default.
- W3039697905 cites W2142641780 @default.
- W3039697905 cites W2156909104 @default.
- W3039697905 cites W2173051530 @default.
- W3039697905 cites W2173183968 @default.
- W3039697905 cites W2194690080 @default.
- W3039697905 cites W2204302769 @default.
- W3039697905 cites W2214429195 @default.
- W3039697905 cites W2244807774 @default.
- W3039697905 cites W2257979135 @default.
- W3039697905 cites W2264259902 @default.
- W3039697905 cites W2294628582 @default.
- W3039697905 cites W2511174833 @default.
- W3039697905 cites W2530887700 @default.
- W3039697905 cites W2555472853 @default.
- W3039697905 cites W2605023530 @default.
- W3039697905 cites W2606780347 @default.
- W3039697905 cites W2607964821 @default.
- W3039697905 cites W2805516822 @default.
- W3039697905 cites W2947096529 @default.
- W3039697905 cites W2950527759 @default.
- W3039697905 cites W2950898700 @default.
- W3039697905 cites W2963220331 @default.
- W3039697905 cites W2963773578 @default.
- W3039697905 cites W2982316857 @default.
- W3039697905 cites W2996037775 @default.
- W3039697905 doi "https://doi.org/10.48550/arxiv.2007.03629" @default.
- W3039697905 hasPublicationYear "2020" @default.
- W3039697905 type Work @default.
- W3039697905 sameAs 3039697905 @default.
- W3039697905 citedByCount "4" @default.
- W3039697905 countsByYear W30396979052021 @default.
- W3039697905 crossrefType "posted-content" @default.
- W3039697905 hasAuthorship W3039697905A5000173050 @default.
- W3039697905 hasAuthorship W3039697905A5003562101 @default.
- W3039697905 hasAuthorship W3039697905A5013834379 @default.
- W3039697905 hasAuthorship W3039697905A5039679910 @default.
- W3039697905 hasBestOaLocation W30396979051 @default.
- W3039697905 hasConcept C111696304 @default.
- W3039697905 hasConcept C113138325 @default.
- W3039697905 hasConcept C11413529 @default.
- W3039697905 hasConcept C119857082 @default.
- W3039697905 hasConcept C126388530 @default.
- W3039697905 hasConcept C134306372 @default.
- W3039697905 hasConcept C136197465 @default.
- W3039697905 hasConcept C154945302 @default.
- W3039697905 hasConcept C15744967 @default.
- W3039697905 hasConcept C177148314 @default.
- W3039697905 hasConcept C202444582 @default.
- W3039697905 hasConcept C23123220 @default.
- W3039697905 hasConcept C33923547 @default.
- W3039697905 hasConcept C41008148 @default.
- W3039697905 hasConcept C50644808 @default.
- W3039697905 hasConcept C77805123 @default.
- W3039697905 hasConcept C80444323 @default.
- W3039697905 hasConcept C88548561 @default.
- W3039697905 hasConcept C9652623 @default.
- W3039697905 hasConcept C97541855 @default.
- W3039697905 hasConceptScore W3039697905C111696304 @default.
- W3039697905 hasConceptScore W3039697905C113138325 @default.
- W3039697905 hasConceptScore W3039697905C11413529 @default.
- W3039697905 hasConceptScore W3039697905C119857082 @default.
- W3039697905 hasConceptScore W3039697905C126388530 @default.
- W3039697905 hasConceptScore W3039697905C134306372 @default.
- W3039697905 hasConceptScore W3039697905C136197465 @default.
- W3039697905 hasConceptScore W3039697905C154945302 @default.
- W3039697905 hasConceptScore W3039697905C15744967 @default.
- W3039697905 hasConceptScore W3039697905C177148314 @default.
- W3039697905 hasConceptScore W3039697905C202444582 @default.
- W3039697905 hasConceptScore W3039697905C23123220 @default.
- W3039697905 hasConceptScore W3039697905C33923547 @default.
- W3039697905 hasConceptScore W3039697905C41008148 @default.
- W3039697905 hasConceptScore W3039697905C50644808 @default.
- W3039697905 hasConceptScore W3039697905C77805123 @default.
- W3039697905 hasConceptScore W3039697905C80444323 @default.
- W3039697905 hasConceptScore W3039697905C88548561 @default.
- W3039697905 hasConceptScore W3039697905C9652623 @default.
- W3039697905 hasConceptScore W3039697905C97541855 @default.
- W3039697905 hasLocation W30396979051 @default.
- W3039697905 hasOpenAccess W3039697905 @default.
- W3039697905 hasPrimaryLocation W30396979051 @default.
- W3039697905 hasRelatedWork W1606678907 @default.
- W3039697905 hasRelatedWork W2432916743 @default.
- W3039697905 hasRelatedWork W2907922678 @default.
- W3039697905 hasRelatedWork W2989932438 @default.
- W3039697905 hasRelatedWork W3011591403 @default.
- W3039697905 hasRelatedWork W3022038857 @default.