Matches in SemOpenAlex for { <https://semopenalex.org/work/W2930904717> ?p ?o ?g. }
- W2930904717 abstract "We describe a method for utilizing the known structure of input data to make learning more efficient. Our work is in the domain of programming languages, and we use deep neural networks to do program analysis. Computer programs include a lot of structural information (such as loop nests, conditional blocks, and data scopes), which is pertinent to program analysis. In this case, the neural network has to learn to recognize the structure, and also learn the target function for the problem. However, the structural information in this domain is readily accessible to software with the availability of compiler tools and parsers for well-defined programming languages. Our method for utilizing the known structure of input data includes: (1) pre-processing the input data to expose relevant structures, and (2) constructing neural networks by incorporating the structure of the input data as an integral part of the network design. The method has the effect of modularizing the neural network which helps break down complexity, and results in more efficient training of the overall network. We apply this method to an example code analysis problem, and show that it can achieve higher accuracy with a smaller network size and fewer training examples. Further, the method is robust, performing equally well on input data with different distributions." @default.
- W2930904717 created "2019-04-11" @default.
- W2930904717 creator A5005051912 @default.
- W2930904717 creator A5072951628 @default.
- W2930904717 creator A5086222900 @default.
- W2930904717 date "2019-03-29" @default.
- W2930904717 modified "2023-09-25" @default.
- W2930904717 title "Using Structured Input and Modularity for Improved Learning" @default.
- W2930904717 cites W1496229274 @default.
- W2930904717 cites W1889268436 @default.
- W2930904717 cites W2032690046 @default.
- W2930904717 cites W2106837051 @default.
- W2930904717 cites W2143545157 @default.
- W2930904717 cites W2162635690 @default.
- W2930904717 cites W2274287116 @default.
- W2930904717 cites W2296073425 @default.
- W2930904717 cites W2511803001 @default.
- W2930904717 cites W2525778437 @default.
- W2930904717 cites W2545625743 @default.
- W2930904717 cites W2571860534 @default.
- W2930904717 cites W2736218237 @default.
- W2930904717 cites W2772752644 @default.
- W2930904717 cites W2786013445 @default.
- W2930904717 cites W2798628553 @default.
- W2930904717 cites W2806157698 @default.
- W2930904717 cites W2963102152 @default.
- W2930904717 cites W2963143606 @default.
- W2930904717 cites W2963223524 @default.
- W2930904717 cites W2963355447 @default.
- W2930904717 cites W2963371736 @default.
- W2930904717 cites W2963393838 @default.
- W2930904717 cites W2963703618 @default.
- W2930904717 hasPublicationYear "2019" @default.
- W2930904717 type Work @default.
- W2930904717 sameAs 2930904717 @default.
- W2930904717 citedByCount "0" @default.
- W2930904717 crossrefType "posted-content" @default.
- W2930904717 hasAuthorship W2930904717A5005051912 @default.
- W2930904717 hasAuthorship W2930904717A5072951628 @default.
- W2930904717 hasAuthorship W2930904717A5086222900 @default.
- W2930904717 hasConcept C119857082 @default.
- W2930904717 hasConcept C124101348 @default.
- W2930904717 hasConcept C134306372 @default.
- W2930904717 hasConcept C154945302 @default.
- W2930904717 hasConcept C162319229 @default.
- W2930904717 hasConcept C169590947 @default.
- W2930904717 hasConcept C177264268 @default.
- W2930904717 hasConcept C186644900 @default.
- W2930904717 hasConcept C199360897 @default.
- W2930904717 hasConcept C2776760102 @default.
- W2930904717 hasConcept C2777904410 @default.
- W2930904717 hasConcept C2779478453 @default.
- W2930904717 hasConcept C33923547 @default.
- W2930904717 hasConcept C36503486 @default.
- W2930904717 hasConcept C41008148 @default.
- W2930904717 hasConcept C50644808 @default.
- W2930904717 hasConcept C54355233 @default.
- W2930904717 hasConcept C80444323 @default.
- W2930904717 hasConcept C86803240 @default.
- W2930904717 hasConceptScore W2930904717C119857082 @default.
- W2930904717 hasConceptScore W2930904717C124101348 @default.
- W2930904717 hasConceptScore W2930904717C134306372 @default.
- W2930904717 hasConceptScore W2930904717C154945302 @default.
- W2930904717 hasConceptScore W2930904717C162319229 @default.
- W2930904717 hasConceptScore W2930904717C169590947 @default.
- W2930904717 hasConceptScore W2930904717C177264268 @default.
- W2930904717 hasConceptScore W2930904717C186644900 @default.
- W2930904717 hasConceptScore W2930904717C199360897 @default.
- W2930904717 hasConceptScore W2930904717C2776760102 @default.
- W2930904717 hasConceptScore W2930904717C2777904410 @default.
- W2930904717 hasConceptScore W2930904717C2779478453 @default.
- W2930904717 hasConceptScore W2930904717C33923547 @default.
- W2930904717 hasConceptScore W2930904717C36503486 @default.
- W2930904717 hasConceptScore W2930904717C41008148 @default.
- W2930904717 hasConceptScore W2930904717C50644808 @default.
- W2930904717 hasConceptScore W2930904717C54355233 @default.
- W2930904717 hasConceptScore W2930904717C80444323 @default.
- W2930904717 hasConceptScore W2930904717C86803240 @default.
- W2930904717 hasLocation W29309047171 @default.
- W2930904717 hasOpenAccess W2930904717 @default.
- W2930904717 hasPrimaryLocation W29309047171 @default.
- W2930904717 hasRelatedWork W1469352018 @default.
- W2930904717 hasRelatedWork W1584616449 @default.
- W2930904717 hasRelatedWork W1696799466 @default.
- W2930904717 hasRelatedWork W2052190470 @default.
- W2930904717 hasRelatedWork W2097557179 @default.
- W2930904717 hasRelatedWork W2164038453 @default.
- W2930904717 hasRelatedWork W2625056554 @default.
- W2930904717 hasRelatedWork W2762491430 @default.
- W2930904717 hasRelatedWork W2798918700 @default.
- W2930904717 hasRelatedWork W2890007640 @default.
- W2930904717 hasRelatedWork W2903224116 @default.
- W2930904717 hasRelatedWork W2963503788 @default.
- W2930904717 hasRelatedWork W2968700020 @default.
- W2930904717 hasRelatedWork W2990448925 @default.
- W2930904717 hasRelatedWork W2995494395 @default.
- W2930904717 hasRelatedWork W2996682448 @default.
- W2930904717 hasRelatedWork W3011075034 @default.
- W2930904717 hasRelatedWork W3092838946 @default.
- W2930904717 hasRelatedWork W3214276846 @default.