FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167756471> ?p ?o ?g. }

• W3167756471 endingPage "2685" @default.
• W3167756471 startingPage "2676" @default.
• W3167756471 abstract "The human brain has evolved to perform complex and computationally expensive cognitive tasks, such as audio-visual perception and object detection, with ease. For instance, the brain can recognize speech in different dialects and perform other cognitive tasks, such as attention, memory, and motor control, with just 20 W of power consumption. Taking inspiration from neural systems, we propose a low-power neuromorphic hardware architecture to perform classification on temporal data at the edge. The proposed architecture uses a neuromorphic cochlea model for feature extraction and reservoir computing (RC) framework as a classifier. In the proposed hardware architecture, the RC framework is modified for on-the-fly generation of reservoir connectivity, along with binary feedforward and reservoir weights. Also, a large reservoir is split into multiple small reservoirs for efficient use of hardware resources. These modifications reduce the computational and memory resources required, thereby resulting in a lower power budget. The proposed classifier is validated for speech and human activity recognition (HAR) tasks. We have prototyped our hardware architecture using Intel's cyclone-10 low-power series field-programmable gate array (FPGA), consuming only 4790 logic elements (LEs) and 34.9-kB memory, making it a perfect candidate for edge computing applications. Moreover, we have implemented a complete system for speech recognition with the feature extraction block (cochlea model) and the proposed classifier, utilizing 15 532 LEs and 38.4-kB memory. By using the proposed idea of multiple small reservoirs along with on-the-fly generation of reservoir binary weights, our architecture can reduce the power consumption and memory requirement by order of magnitude compared to existing FPGA models for speech recognition tasks with similar complexity." @default.
• W3167756471 created "2021-06-22" @default.
• W3167756471 creator A5017300759 @default.
• W3167756471 creator A5085211717 @default.
• W3167756471 creator A5085605365 @default.
• W3167756471 date "2022-06-01" @default.
• W3167756471 modified "2023-09-25" @default.
• W3167756471 title "Neuromorphic Time-Multiplexed Reservoir Computing With On-the-Fly Weight Generation for Edge Devices" @default.
• W3167756471 cites W1646015841 @default.
• W3167756471 cites W1970787568 @default.
• W3167756471 cites W2012557818 @default.
• W3167756471 cites W2037024114 @default.
• W3167756471 cites W2054965558 @default.
• W3167756471 cites W2061179798 @default.
• W3167756471 cites W2097309428 @default.
• W3167756471 cites W2097575504 @default.
• W3167756471 cites W2109447493 @default.
• W3167756471 cites W2113498576 @default.
• W3167756471 cites W2123504417 @default.
• W3167756471 cites W2134603460 @default.
• W3167756471 cites W2142274998 @default.
• W3167756471 cites W2149530067 @default.
• W3167756471 cites W2156640153 @default.
• W3167756471 cites W2159682675 @default.
• W3167756471 cites W2171865010 @default.
• W3167756471 cites W2195342085 @default.
• W3167756471 cites W2311161367 @default.
• W3167756471 cites W2416799949 @default.
• W3167756471 cites W2518582440 @default.
• W3167756471 cites W2529096783 @default.
• W3167756471 cites W2560918633 @default.
• W3167756471 cites W2585720638 @default.
• W3167756471 cites W2612464443 @default.
• W3167756471 cites W2767979715 @default.
• W3167756471 cites W2782994703 @default.
• W3167756471 cites W2791133433 @default.
• W3167756471 cites W2798156395 @default.
• W3167756471 cites W2887258823 @default.
• W3167756471 cites W2943148367 @default.
• W3167756471 cites W2964010909 @default.
• W3167756471 cites W2979872424 @default.
• W3167756471 cites W3015505405 @default.
• W3167756471 cites W3034039317 @default.
• W3167756471 cites W3038427506 @default.
• W3167756471 cites W3098369763 @default.
• W3167756471 cites W3098613138 @default.
• W3167756471 doi "https://doi.org/10.1109/tnnls.2021.3085165" @default.
• W3167756471 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34125686" @default.
• W3167756471 hasPublicationYear "2022" @default.
• W3167756471 type Work @default.
• W3167756471 sameAs 3167756471 @default.
• W3167756471 citedByCount "2" @default.
• W3167756471 countsByYear W31677564712021 @default.
• W3167756471 countsByYear W31677564712023 @default.
• W3167756471 crossrefType "journal-article" @default.
• W3167756471 hasAuthorship W3167756471A5017300759 @default.
• W3167756471 hasAuthorship W3167756471A5085211717 @default.
• W3167756471 hasAuthorship W3167756471A5085605365 @default.
• W3167756471 hasConcept C135796866 @default.
• W3167756471 hasConcept C147168706 @default.
• W3167756471 hasConcept C151927369 @default.
• W3167756471 hasConcept C153180895 @default.
• W3167756471 hasConcept C154945302 @default.
• W3167756471 hasConcept C162307627 @default.
• W3167756471 hasConcept C169760540 @default.
• W3167756471 hasConcept C169900460 @default.
• W3167756471 hasConcept C20854674 @default.
• W3167756471 hasConcept C2778456923 @default.
• W3167756471 hasConcept C41008148 @default.
• W3167756471 hasConcept C42935608 @default.
• W3167756471 hasConcept C50644808 @default.
• W3167756471 hasConcept C52622490 @default.
• W3167756471 hasConcept C86803240 @default.
• W3167756471 hasConcept C9390403 @default.
• W3167756471 hasConcept C95623464 @default.
• W3167756471 hasConceptScore W3167756471C135796866 @default.
• W3167756471 hasConceptScore W3167756471C147168706 @default.
• W3167756471 hasConceptScore W3167756471C151927369 @default.
• W3167756471 hasConceptScore W3167756471C153180895 @default.
• W3167756471 hasConceptScore W3167756471C154945302 @default.
• W3167756471 hasConceptScore W3167756471C162307627 @default.
• W3167756471 hasConceptScore W3167756471C169760540 @default.
• W3167756471 hasConceptScore W3167756471C169900460 @default.
• W3167756471 hasConceptScore W3167756471C20854674 @default.
• W3167756471 hasConceptScore W3167756471C2778456923 @default.
• W3167756471 hasConceptScore W3167756471C41008148 @default.
• W3167756471 hasConceptScore W3167756471C42935608 @default.
• W3167756471 hasConceptScore W3167756471C50644808 @default.
• W3167756471 hasConceptScore W3167756471C52622490 @default.
• W3167756471 hasConceptScore W3167756471C86803240 @default.
• W3167756471 hasConceptScore W3167756471C9390403 @default.
• W3167756471 hasConceptScore W3167756471C95623464 @default.
• W3167756471 hasFunder F4320329120 @default.
• W3167756471 hasFunder F4320334771 @default.
• W3167756471 hasIssue "6" @default.
• W3167756471 hasLocation W31677564711 @default.
• W3167756471 hasLocation W31677564712 @default.
• W3167756471 hasOpenAccess W3167756471 @default.

• next