FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328105391> ?p ?o ?g. }

• W4328105391 endingPage "540" @default.
• W4328105391 startingPage "531" @default.
• W4328105391 abstract "In this paper we present CHARLES (C++ pHotonic Aware neuRaL nEtworkS), a C++ library aimed at providing a flexible tool to simulate the behavior of Photonic-Aware Neural Network (PANN). PANNs are neural network architectures aware of the constraints due to the underlying photonic hardware, mostly in terms of low equivalent precision of the computations. For this reason, CHARLES exploits fixed-point computations for inference, while it supports both floating-point and fixed-point numerical formats for training. In this way, we can compare the effects due to the quantization in the inference phase when the training phase is performed on a classical floating-point model and on a model exploiting high-precision fixed-point numbers. To validate CHARLES and identify the most suited numerical format for PANN training, we report the simulation results obtained considering three datasets: Iris, MNIST, and Fashion-MNIST. Fixed-training is shown to outperform floating-training when executing inference on bitwidths suitable for photonic implementation. Indeed, performing the training phase in the floating-point domain and then quantizing to lower bitwidths results in a very high accuracy loss. Instead, when fixed-point numbers are exploited in the training phase, the accuracy loss due to quantization to lower bitwidths is significantly reduced. In particular, we show that for Iris dataset, fixed-training achieves a performance similar to floating-training. Fixed-training allows to obtain an accuracy of 90.4% and 68.1% with the MNIST and Fashion-MNIST datasets using only 6 bits, while the floating-training reaches an accuracy of just 25.4% and 50.0% when exploiting the same bitwidths." @default.
• W4328105391 created "2023-03-22" @default.
• W4328105391 creator A5016101884 @default.
• W4328105391 creator A5024138045 @default.
• W4328105391 creator A5066928855 @default.
• W4328105391 creator A5072597020 @default.
• W4328105391 creator A5080905811 @default.
• W4328105391 date "2023-05-01" @default.
• W4328105391 modified "2023-09-27" @default.
• W4328105391 title "CHARLES: A C++ fixed-point library for Photonic-Aware Neural Networks" @default.
• W4328105391 cites W1963930425 @default.
• W4328105391 cites W2003811155 @default.
• W4328105391 cites W2007339694 @default.
• W4328105391 cites W2051270432 @default.
• W4328105391 cites W2083936311 @default.
• W4328105391 cites W2112796928 @default.
• W4328105391 cites W2604319603 @default.
• W4328105391 cites W2739588406 @default.
• W4328105391 cites W2752849906 @default.
• W4328105391 cites W2798701005 @default.
• W4328105391 cites W2803450791 @default.
• W4328105391 cites W2884367402 @default.
• W4328105391 cites W2887566712 @default.
• W4328105391 cites W2904694042 @default.
• W4328105391 cites W2921972904 @default.
• W4328105391 cites W2923980602 @default.
• W4328105391 cites W2944119451 @default.
• W4328105391 cites W2953409933 @default.
• W4328105391 cites W2961408049 @default.
• W4328105391 cites W2974263490 @default.
• W4328105391 cites W2992359756 @default.
• W4328105391 cites W3034940165 @default.
• W4328105391 cites W3103046660 @default.
• W4328105391 cites W3107308400 @default.
• W4328105391 cites W3128451613 @default.
• W4328105391 cites W3131200591 @default.
• W4328105391 cites W3157721836 @default.
• W4328105391 cites W4285215295 @default.
• W4328105391 cites W4308514394 @default.
• W4328105391 cites W4312263904 @default.
• W4328105391 doi "https://doi.org/10.1016/j.neunet.2023.03.007" @default.
• W4328105391 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36990002" @default.
• W4328105391 hasPublicationYear "2023" @default.
• W4328105391 type Work @default.
• W4328105391 citedByCount "0" @default.
• W4328105391 crossrefType "journal-article" @default.
• W4328105391 hasAuthorship W4328105391A5016101884 @default.
• W4328105391 hasAuthorship W4328105391A5024138045 @default.
• W4328105391 hasAuthorship W4328105391A5066928855 @default.
• W4328105391 hasAuthorship W4328105391A5072597020 @default.
• W4328105391 hasAuthorship W4328105391A5080905811 @default.
• W4328105391 hasConcept C11413529 @default.
• W4328105391 hasConcept C120665830 @default.
• W4328105391 hasConcept C121332964 @default.
• W4328105391 hasConcept C134306372 @default.
• W4328105391 hasConcept C154945302 @default.
• W4328105391 hasConcept C190502265 @default.
• W4328105391 hasConcept C20788544 @default.
• W4328105391 hasConcept C2776214188 @default.
• W4328105391 hasConcept C28855332 @default.
• W4328105391 hasConcept C33923547 @default.
• W4328105391 hasConcept C41008148 @default.
• W4328105391 hasConcept C45374587 @default.
• W4328105391 hasConcept C50644808 @default.
• W4328105391 hasConcept C61445026 @default.
• W4328105391 hasConcept C84211073 @default.
• W4328105391 hasConceptScore W4328105391C11413529 @default.
• W4328105391 hasConceptScore W4328105391C120665830 @default.
• W4328105391 hasConceptScore W4328105391C121332964 @default.
• W4328105391 hasConceptScore W4328105391C134306372 @default.
• W4328105391 hasConceptScore W4328105391C154945302 @default.
• W4328105391 hasConceptScore W4328105391C190502265 @default.
• W4328105391 hasConceptScore W4328105391C20788544 @default.
• W4328105391 hasConceptScore W4328105391C2776214188 @default.
• W4328105391 hasConceptScore W4328105391C28855332 @default.
• W4328105391 hasConceptScore W4328105391C33923547 @default.
• W4328105391 hasConceptScore W4328105391C41008148 @default.
• W4328105391 hasConceptScore W4328105391C45374587 @default.
• W4328105391 hasConceptScore W4328105391C50644808 @default.
• W4328105391 hasConceptScore W4328105391C61445026 @default.
• W4328105391 hasConceptScore W4328105391C84211073 @default.
• W4328105391 hasFunder F4320321873 @default.
• W4328105391 hasFunder F4320322651 @default.
• W4328105391 hasFunder F4320327207 @default.
• W4328105391 hasFunder F4320334322 @default.
• W4328105391 hasFunder F4320335254 @default.
• W4328105391 hasLocation W43281053911 @default.
• W4328105391 hasLocation W43281053912 @default.
• W4328105391 hasOpenAccess W4328105391 @default.
• W4328105391 hasPrimaryLocation W43281053911 @default.
• W4328105391 hasRelatedWork W2765402136 @default.
• W4328105391 hasRelatedWork W2777406049 @default.
• W4328105391 hasRelatedWork W2803935332 @default.
• W4328105391 hasRelatedWork W2891335318 @default.
• W4328105391 hasRelatedWork W2966207885 @default.
• W4328105391 hasRelatedWork W4280607397 @default.
• W4328105391 hasRelatedWork W4297196174 @default.
• W4328105391 hasRelatedWork W4321472478 @default.

• next