{"id":"https://openalex.org/W7217675147","doi":null,"title":"Methods and Applications for Low-power Deep Neural Networks on Edge Devices","display_name":"Methods and Applications for Low-power Deep Neural Networks on Edge Devices","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W7217675147"},"language":"en","primary_location":{"id":"pmh:oai:iris.polito.it:11583/2976593","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11583/2976593","pdf_url":"https://iris.polito.it/bitstream/11583/2976593/2/conv_phd_thesis_reviewed.pdf","source":{"id":"https://openalex.org/S7407055329","display_name":"PORTO@Iris","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://iris.polito.it/bitstream/11583/2976593/2/conv_phd_thesis_reviewed.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032387854","display_name":"Luciano Prono","orcid":"https://orcid.org/0000-0003-1507-9092","observed_orcids":["https://orcid.org/0000-0003-1507-9092"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"PRONO, LUCIANO","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5032387854"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7813000082969666,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7813000082969666,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.08990000188350677,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.04520000144839287,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/tinyml","display_name":"TinyML","score":0.8579999804496765},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.9679999947547913},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.9620000123977661},{"id":"https://openalex.org/keywords/parameter-quantization","display_name":"parameter quantization","score":0.8709999918937683},{"id":"https://openalex.org/keywords/recurrent-spiking-neural-networks","display_name":"recurrent spiking neural networks","score":0.9829999804496765},{"id":"https://openalex.org/keywords/compressed-sensing","display_name":"compressed sensing","score":0.8209999799728394},{"id":"https://openalex.org/keywords/signal-reconstruction","display_name":"signal reconstruction","score":0.9539999961853027},{"id":"https://openalex.org/keywords/hardware-compression","display_name":"hardware compression","score":0.7210000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5831000208854675},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210999846458435},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.374099999666214},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3052000105381012},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3019999861717224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28760001063346863}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:iris.polito.it:11583/2976593","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11583/2976593","pdf_url":"https://iris.polito.it/bitstream/11583/2976593/2/conv_phd_thesis_reviewed.pdf","source":{"id":"https://openalex.org/S7407055329","display_name":"PORTO@Iris","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"}],"best_oa_location":{"id":"pmh:oai:iris.polito.it:11583/2976593","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11583/2976593","pdf_url":"https://iris.polito.it/bitstream/11583/2976593/2/conv_phd_thesis_reviewed.pdf","source":{"id":"https://openalex.org/S7407055329","display_name":"PORTO@Iris","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7217675147.pdf","grobid_xml":"https://content.openalex.org/works/W7217675147.grobid-xml"},"referenced_works_count":87,"referenced_works":["https://openalex.org/W946256365","https://openalex.org/W1422049004","https://openalex.org/W1849787805","https://openalex.org/W1931873216","https://openalex.org/W1966602924","https://openalex.org/W1972091546","https://openalex.org/W1972967427","https://openalex.org/W1973711324","https://openalex.org/W1974812526","https://openalex.org/W1976426522","https://openalex.org/W1986650185","https://openalex.org/W1999954155","https://openalex.org/W2013024221","https://openalex.org/W2029816571","https://openalex.org/W2032712527","https://openalex.org/W2041046019","https://openalex.org/W2054669701","https://openalex.org/W2083663865","https://openalex.org/W2089243291","https://openalex.org/W2092400178","https://openalex.org/W2100556411","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2126311411","https://openalex.org/W2127271355","https://openalex.org/W2129131372","https://openalex.org/W2130459697","https://openalex.org/W2131496831","https://openalex.org/W2132904166","https://openalex.org/W2134207998","https://openalex.org/W2141840773","https://openalex.org/W2145096794","https://openalex.org/W2147465462","https://openalex.org/W2150355110","https://openalex.org/W2153945778","https://openalex.org/W2154483232","https://openalex.org/W2162800060","https://openalex.org/W2166670884","https://openalex.org/W2176563895","https://openalex.org/W2273561594","https://openalex.org/W2289917018","https://openalex.org/W2300242332","https://openalex.org/W2301380833","https://openalex.org/W2319920447","https://openalex.org/W2394634174","https://openalex.org/W2416799949","https://openalex.org/W2507344106","https://openalex.org/W2510572839","https://openalex.org/W2578009003","https://openalex.org/W2578406593","https://openalex.org/W2745933219","https://openalex.org/W2756336019","https://openalex.org/W2794584188","https://openalex.org/W2798878556","https://openalex.org/W2809334893","https://openalex.org/W2888502647","https://openalex.org/W2920535273","https://openalex.org/W2921746183","https://openalex.org/W2941290925","https://openalex.org/W2962818002","https://openalex.org/W2963319203","https://openalex.org/W2963363373","https://openalex.org/W2964121744","https://openalex.org/W2972645737","https://openalex.org/W2979314664","https://openalex.org/W2983605412","https://openalex.org/W2996874060","https://openalex.org/W3006413273","https://openalex.org/W3014020978","https://openalex.org/W3014641619","https://openalex.org/W3035000326","https://openalex.org/W3043133474","https://openalex.org/W3089699294","https://openalex.org/W3097140984","https://openalex.org/W3107308437","https://openalex.org/W3135205958","https://openalex.org/W3135547017","https://openalex.org/W3153990350","https://openalex.org/W3180051575","https://openalex.org/W3213864175","https://openalex.org/W3216221236","https://openalex.org/W4200186958","https://openalex.org/W4213060227","https://openalex.org/W4220741568","https://openalex.org/W4250955649","https://openalex.org/W4309242452","https://openalex.org/W6922493320"],"related_works":["https://openalex.org/W7216796147","https://openalex.org/W7219434685","https://openalex.org/W7130556941","https://openalex.org/W7217723148","https://openalex.org/W6928845541","https://openalex.org/W7216798996","https://openalex.org/W3157088340","https://openalex.org/W7130548234","https://openalex.org/W7216910367","https://openalex.org/W7020743575"],"abstract_inverted_index":{"Methods":[0],"and":[1,61,90,105,131,138,146,158,164,167,169,172,259],"Applications":[2],"for":[3,133],"Low-Power":[4],"Deep":[5,32],"Neural":[6,33,217],"Networks":[7,34],"on":[8,59,97,128,237],"Edge":[9,91,111],"Devices":[10],"by":[11],"Luciano":[12],"PRONO":[13],"Machine":[14],"Learning":[15],"(ML)":[16],"techniques":[17,266],"introduce":[18,143,231],"the":[19,43,52,55,83,98,123,129,134,185,198,227,241,247,277,280,296],"possibility":[20],"of":[21,29,45,49,57,77,85,87,100,136,193,213,269,271,276,279,283],"solving":[22],"many":[23],"complex":[24],"tasks":[25],"requiring":[26],"humongous":[27],"amounts":[28],"data.In":[30],"particular,":[31],"(DNNs)":[35],"are":[36,181],"structures":[37,104],"that":[38,180,300],"provide":[39],"excellent":[40],"results":[41],"with":[42,64,109,200,246],"use":[44,174],"a":[46,74,194,214,232],"massive":[47],"number":[48,76],"trainable":[50],"parameters.At":[51],"same":[53],"time,":[54],"implementation":[56,192,199,212],"DNNs":[58],"cheap":[60],"low-power":[62,137,221],"devices":[63],"high":[65],"resource":[66],"constraints,":[67],"referred":[68],"to":[69,156,176,184,223,286,294,304],"as":[70,115],"tinyML,":[71],"would":[72,204],"unlock":[73],"large":[75],"entirely":[78],"new":[79],"applications":[80],"possible":[81],"in":[82,251,267],"fields":[84],"Internet":[86],"Things":[88],"(IoT)":[89],"Computing.In":[92],"this":[93,284,289,301],"dissertation,":[94],"we":[95,106,126,142,150,173,188,208,230,239,273],"focus":[96,127],"design":[99,135],"low-power,":[101],"low-memory":[102],"DNN":[103,140,178],"implement":[107],"them":[108,175],"novel":[110,153,233,242,262,302],"Computing":[112],"approaches":[113],"such":[114],"an":[116,190,210],"innovative":[117],"Compressed":[118],"Sensing":[119],"(CS)":[120],"DNN-based":[121],"decoder.In":[122],"first":[124,281],"part,":[125,229],"methods":[130,278],"architectures":[132],"tiny":[139],"structures.Firstly,":[141],"parameters":[144],"quantization":[145],"interconnection":[147],"pruning":[148,186],"methods.Secondly,":[149],"present":[151,189,209],"two":[152,252],"map-reduce":[154],"alternatives":[155],"Multiply":[157,168],"Accumulate":[159],"(MAC)":[160],"paradigm,":[161],"namely":[162,256],"Sum":[163],"Max":[165],"(SAM)":[166],"Max-Min":[170],"(MAM\u00b2),":[171],"build":[177],"layers":[179,203],"highly":[182],"resistant":[183],"process.Additionally,":[187],"on-device":[191,211],"MAM\u00b2":[195],"layer,":[196],"where":[197],"standard":[201],"MAC-based":[202],"not":[205],"be":[206,292],"possible.Finally,":[207],"Recurrent":[215],"Spiking":[216],"Network":[218],"(RSNN),":[219],"intrinsically":[220],"due":[222],"its":[224],"sparsity":[225],"properties.In":[226],"second":[228],"CS":[234,244,305],"decoder":[235],"based":[236],"DNNs.Firstly,":[238],"describe":[240],"encoding-decoding":[243],"framework,":[245],"decoding":[248],"phase":[249],"split":[250],"distinct":[253],"working":[254],"blocks,":[255],"support":[257],"retrieval":[258],"signal":[260],"reconstruction.This":[261],"approach":[263,303],"outperforms":[264],"state-of-the-art":[265],"terms":[268],"quality":[270],"reconstruction.Finally,":[272],"apply":[274],"some":[275],"part":[282],"dissertation":[285],"study":[287],"how":[288],"structure":[290],"can":[291],"compressed":[293],"reduce":[295],"hardware":[297],"requirements,":[298],"showing":[299],"needs":[306],"very":[307],"few":[308],"resources.":[309]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-03T00:00:00"}