Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385245476> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4385245476 abstract "Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotion), similar to humans. Recent research has shown that multi-input single-output (MISO) deep neural networks (DNN) outperform traditional single-input single-output (SISO) models, representing a significant step towards this goal. In this paper, we propose MIMONet, a novel on-device multi-input multi-output (MIMO) DNN framework that achieves high accuracy and on-device efficiency in terms of critical performance metrics such as latency, energy, and memory usage. Leveraging existing SISO model compression techniques, MIMONet develops a new deep-compression method that is specifically tailored to MIMO models. This new method explores unique yet non-trivial properties of the MIMO model, resulting in boosted accuracy and on-device efficiency. Extensive experiments on three embedded platforms commonly used in robotic systems, as well as a case study using the TurtleBot3 robot, demonstrate that MIMONet achieves higher accuracy and superior on-device efficiency compared to state-of-the-art SISO and MISO models, as well as a baseline MIMO model we constructed. Our evaluation highlights the real-world applicability of MIMONet and its potential to significantly enhance the performance of intelligent robotic systems." @default.
- W4385245476 created "2023-07-26" @default.
- W4385245476 creator A5008651676 @default.
- W4385245476 creator A5009841558 @default.
- W4385245476 creator A5042361412 @default.
- W4385245476 creator A5052569205 @default.
- W4385245476 creator A5053592535 @default.
- W4385245476 creator A5060999697 @default.
- W4385245476 creator A5091919097 @default.
- W4385245476 date "2023-07-21" @default.
- W4385245476 modified "2023-10-14" @default.
- W4385245476 title "MIMONet: Multi-Input Multi-Output On-Device Deep Learning" @default.
- W4385245476 doi "https://doi.org/10.48550/arxiv.2307.11962" @default.
- W4385245476 hasPublicationYear "2023" @default.
- W4385245476 type Work @default.
- W4385245476 citedByCount "0" @default.
- W4385245476 crossrefType "posted-content" @default.
- W4385245476 hasAuthorship W4385245476A5008651676 @default.
- W4385245476 hasAuthorship W4385245476A5009841558 @default.
- W4385245476 hasAuthorship W4385245476A5042361412 @default.
- W4385245476 hasAuthorship W4385245476A5052569205 @default.
- W4385245476 hasAuthorship W4385245476A5053592535 @default.
- W4385245476 hasAuthorship W4385245476A5060999697 @default.
- W4385245476 hasAuthorship W4385245476A5091919097 @default.
- W4385245476 hasBestOaLocation W43852454761 @default.
- W4385245476 hasConcept C108583219 @default.
- W4385245476 hasConcept C111919701 @default.
- W4385245476 hasConcept C113775141 @default.
- W4385245476 hasConcept C127162648 @default.
- W4385245476 hasConcept C154945302 @default.
- W4385245476 hasConcept C207987634 @default.
- W4385245476 hasConcept C2984842247 @default.
- W4385245476 hasConcept C41008148 @default.
- W4385245476 hasConcept C50644808 @default.
- W4385245476 hasConcept C76155785 @default.
- W4385245476 hasConcept C82876162 @default.
- W4385245476 hasConcept C90509273 @default.
- W4385245476 hasConcept C98045186 @default.
- W4385245476 hasConceptScore W4385245476C108583219 @default.
- W4385245476 hasConceptScore W4385245476C111919701 @default.
- W4385245476 hasConceptScore W4385245476C113775141 @default.
- W4385245476 hasConceptScore W4385245476C127162648 @default.
- W4385245476 hasConceptScore W4385245476C154945302 @default.
- W4385245476 hasConceptScore W4385245476C207987634 @default.
- W4385245476 hasConceptScore W4385245476C2984842247 @default.
- W4385245476 hasConceptScore W4385245476C41008148 @default.
- W4385245476 hasConceptScore W4385245476C50644808 @default.
- W4385245476 hasConceptScore W4385245476C76155785 @default.
- W4385245476 hasConceptScore W4385245476C82876162 @default.
- W4385245476 hasConceptScore W4385245476C90509273 @default.
- W4385245476 hasConceptScore W4385245476C98045186 @default.
- W4385245476 hasLocation W43852454761 @default.
- W4385245476 hasOpenAccess W4385245476 @default.
- W4385245476 hasPrimaryLocation W43852454761 @default.
- W4385245476 hasRelatedWork W2279398222 @default.
- W4385245476 hasRelatedWork W2791691546 @default.
- W4385245476 hasRelatedWork W2915754718 @default.
- W4385245476 hasRelatedWork W2941846814 @default.
- W4385245476 hasRelatedWork W3082895349 @default.
- W4385245476 hasRelatedWork W3176779650 @default.
- W4385245476 hasRelatedWork W3193983877 @default.
- W4385245476 hasRelatedWork W4298388782 @default.
- W4385245476 hasRelatedWork W4299822940 @default.
- W4385245476 hasRelatedWork W4312831135 @default.
- W4385245476 isParatext "false" @default.
- W4385245476 isRetracted "false" @default.
- W4385245476 workType "article" @default.