Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308731133> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4308731133 endingPage "20" @default.
- W4308731133 startingPage "1" @default.
- W4308731133 abstract "With the popularity of deep learning, the hardware implementation platform of deep learning has received increasing interest. Unlike the general purpose devices, e.g., CPU or GPU, where the deep learning algorithms are executed at the software level, neural network hardware accelerators directly execute the algorithms to achieve higher energy efficiency and performance improvements. However, as the deep learning algorithms evolve frequently, the engineering effort and cost of designing the hardware accelerators are greatly increased. To improve the design quality while saving the cost, design automation for neural network accelerators was proposed, where design space exploration algorithms are used to automatically search the optimized accelerator design within a design space. Nevertheless, the increasing complexity of the neural network accelerators brings the increasing dimensions to the design space. As a result, the previous design space exploration algorithms are no longer effective enough to find an optimized design. In this work, we propose a neural network accelerator design automation framework named GANDSE, where we rethink the problem of design space exploration, and propose a novel approach based on the generative adversarial network (GAN) to support an optimized exploration for high-dimension large design space. The experiments show that GANDSE is able to find the more optimized designs in negligible time compared with approaches including multilayer perceptron and deep reinforcement learning." @default.
- W4308731133 created "2022-11-15" @default.
- W4308731133 creator A5019399075 @default.
- W4308731133 creator A5047445405 @default.
- W4308731133 creator A5050611867 @default.
- W4308731133 creator A5054211420 @default.
- W4308731133 creator A5056805627 @default.
- W4308731133 creator A5058156841 @default.
- W4308731133 date "2023-03-19" @default.
- W4308731133 modified "2023-09-28" @default.
- W4308731133 title "GANDSE: Generative Adversarial Network-based Design Space Exploration for Neural Network Accelerator Design" @default.
- W4308731133 cites W2289252105 @default.
- W4308731133 cites W2522548197 @default.
- W4308731133 cites W2975468520 @default.
- W4308731133 cites W3090389586 @default.
- W4308731133 cites W3096831136 @default.
- W4308731133 cites W3100638618 @default.
- W4308731133 cites W4293026115 @default.
- W4308731133 doi "https://doi.org/10.1145/3570926" @default.
- W4308731133 hasPublicationYear "2023" @default.
- W4308731133 type Work @default.
- W4308731133 citedByCount "0" @default.
- W4308731133 crossrefType "journal-article" @default.
- W4308731133 hasAuthorship W4308731133A5019399075 @default.
- W4308731133 hasAuthorship W4308731133A5047445405 @default.
- W4308731133 hasAuthorship W4308731133A5050611867 @default.
- W4308731133 hasAuthorship W4308731133A5054211420 @default.
- W4308731133 hasAuthorship W4308731133A5056805627 @default.
- W4308731133 hasAuthorship W4308731133A5058156841 @default.
- W4308731133 hasBestOaLocation W43087311331 @default.
- W4308731133 hasConcept C104060986 @default.
- W4308731133 hasConcept C108583219 @default.
- W4308731133 hasConcept C113775141 @default.
- W4308731133 hasConcept C118524514 @default.
- W4308731133 hasConcept C119857082 @default.
- W4308731133 hasConcept C121332964 @default.
- W4308731133 hasConcept C127413603 @default.
- W4308731133 hasConcept C1276947 @default.
- W4308731133 hasConcept C146978453 @default.
- W4308731133 hasConcept C149635348 @default.
- W4308731133 hasConcept C154945302 @default.
- W4308731133 hasConcept C187107819 @default.
- W4308731133 hasConcept C2776221188 @default.
- W4308731133 hasConcept C29829512 @default.
- W4308731133 hasConcept C41008148 @default.
- W4308731133 hasConcept C50644808 @default.
- W4308731133 hasConcept C64260653 @default.
- W4308731133 hasConcept C97541855 @default.
- W4308731133 hasConceptScore W4308731133C104060986 @default.
- W4308731133 hasConceptScore W4308731133C108583219 @default.
- W4308731133 hasConceptScore W4308731133C113775141 @default.
- W4308731133 hasConceptScore W4308731133C118524514 @default.
- W4308731133 hasConceptScore W4308731133C119857082 @default.
- W4308731133 hasConceptScore W4308731133C121332964 @default.
- W4308731133 hasConceptScore W4308731133C127413603 @default.
- W4308731133 hasConceptScore W4308731133C1276947 @default.
- W4308731133 hasConceptScore W4308731133C146978453 @default.
- W4308731133 hasConceptScore W4308731133C149635348 @default.
- W4308731133 hasConceptScore W4308731133C154945302 @default.
- W4308731133 hasConceptScore W4308731133C187107819 @default.
- W4308731133 hasConceptScore W4308731133C2776221188 @default.
- W4308731133 hasConceptScore W4308731133C29829512 @default.
- W4308731133 hasConceptScore W4308731133C41008148 @default.
- W4308731133 hasConceptScore W4308731133C50644808 @default.
- W4308731133 hasConceptScore W4308731133C64260653 @default.
- W4308731133 hasConceptScore W4308731133C97541855 @default.
- W4308731133 hasFunder F4320321001 @default.
- W4308731133 hasFunder F4320331107 @default.
- W4308731133 hasFunder F4320335777 @default.
- W4308731133 hasIssue "3" @default.
- W4308731133 hasLocation W43087311331 @default.
- W4308731133 hasLocation W43087311332 @default.
- W4308731133 hasOpenAccess W4308731133 @default.
- W4308731133 hasPrimaryLocation W43087311331 @default.
- W4308731133 hasRelatedWork W3014300295 @default.
- W4308731133 hasRelatedWork W3164822677 @default.
- W4308731133 hasRelatedWork W4223943233 @default.
- W4308731133 hasRelatedWork W4225161397 @default.
- W4308731133 hasRelatedWork W4250304930 @default.
- W4308731133 hasRelatedWork W4312200629 @default.
- W4308731133 hasRelatedWork W4360585206 @default.
- W4308731133 hasRelatedWork W4364306694 @default.
- W4308731133 hasRelatedWork W4380075502 @default.
- W4308731133 hasRelatedWork W4380086463 @default.
- W4308731133 hasVolume "28" @default.
- W4308731133 isParatext "false" @default.
- W4308731133 isRetracted "false" @default.
- W4308731133 workType "article" @default.