LEADER 01092nam0-22003251i-450- 001 990005881220403321 005 20070112131129.0 010 $a88-86166-17-6 035 $a000588122 035 $aFED01000588122 035 $a(Aleph)000588122FED01 035 $a000588122 100 $a20000421d1994----km-y0itay50------ba 101 0 $aita 105 $a--------101yy 200 1 $aLUIGI Luzzatti e il suo tempo$eatti del convegno internazionale di studio, Venezia, 7-9 novembre 1991$fraccolti da Pier Luigi Ballini e Paolo Pecorari. 210 $cIstituto veneto di scienze lettere ed arti$aVenezia$d1994 215 $a557 p.$d24 cm 225 1 $aBiblioteca luzzattiana. Fonti e studi$v2 610 0 $aLuzzatti, Luigi$aCongressi$a1991 676 $a945.0842$v21$zita 702 1$aBallini,$bPier Luigi$f<1942- > 702 1$aPecorari,$bPaolo 801 0$aIT$bUNINA$gRICA$2UNIMARC 901 $aBK 912 $a990005881220403321 952 $a945.084 CONV VENEZIA 1991 (BIS)$bBibl.30835$fFLFBC 959 $aFLFBC 996 $aLuigi Luzzatti e il suo tempo$9286621 997 $aUNINA LEADER 00860nam0-22003011i-450- 001 990003109130403321 035 $a000310913 035 $aFED01000310913 035 $a(Aleph)000310913FED01 035 $a000310913 100 $a20000920d1988----km-y0itay50------ba 101 0 $aita 102 $aIT 200 1 $a<>investimenti in infrastrutture di trasporto nell'area napoletana$eRapporto 1988$fa cura di Roberto Gerundo. 210 $aNapoli$cCUEN$d1988. 215 $a213 p.$d29 cm 676 $aF/1.4113 676 $aH/3.2 676 $aL/3.2 702 1$aGerundo,$bRoberto 801 0$aIT$bUNINA$gRICA$2UNIMARC 901 $aBK 912 $a990003109130403321 952 $aH/3.2 INV/N.A$b8325$fSES 959 $aSES 996 $aInvestimenti in infrastrutture di trasporto nell'area napoletana$9462344 997 $aUNINA DB $aING01 LEADER 04103nam 2201009z- 450 001 9910557553903321 005 20210501 035 $a(CKB)5400000000044067 035 $a(oapen)https://directory.doabooks.org/handle/20.500.12854/68541 035 $a(oapen)doab68541 035 $a(EXLCZ)995400000000044067 100 $a20202105d2021 |y 0 101 0 $aeng 135 $aurmn|---annan 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 00$aInnovative Topologies and Algorithms for Neural Networks 210 $aBasel, Switzerland$cMDPI - Multidisciplinary Digital Publishing Institute$d2021 215 $a1 online resource (198 p.) 311 08$a3-0365-0284-X 311 08$a3-0365-0285-8 330 $aThe introduction of new topologies and training procedures to deep neural networks has solicited a renewed interest in the field of neural computation. The use of deep structures has significantly improved state-of-the-art applications in many fields, such as computer vision, speech and text processing, medical applications, and IoT (Internet of Things). The probability of a successful outcome from a neural network is linked to selection of an appropriate network architecture and training algorithm. Accordingly, much of the recent research on neural networks has been devoted to the study and proposal of novel architectures, including solutions tailored to specific problems. This book gives significant contributions to the above-mentioned fields by merging theoretical aspects and relevant applications. 606 $aInformation technology industries$2bicssc 610 $a3D convolution neural network 610 $aaction recognition 610 $aalternative fusion neural network 610 $aArabic named entity recognition 610 $aattention mechanism 610 $aautoencoders 610 $abidirectional gated recurrent unit 610 $abidirectional recurrent neural network 610 $aChinese text classification 610 $aCNN 610 $aconvolution neural Networks 610 $aconvolutional neural network 610 $aconvolutional neural networks 610 $adeep convolutional neural networks 610 $adeep learning 610 $adistributed systems 610 $aelements recognition 610 $aembedded deep learning 610 $afacial image analysis 610 $afacial nerve paralysis 610 $afeature fusion 610 $afully convolutional network 610 $afused features 610 $agesture recognition 610 $agradient-weighted class activation maps 610 $agraph convolutional network 610 $agraph partitioning 610 $aGRU 610 $ahuman computer interaction 610 $aimage classification 610 $aInternet of Things 610 $aIoT (Internet of Thing) systems 610 $alinguistic features 610 $along short-term memory 610 $along short-term-memory 610 $along-short-term memory networks 610 $aLSTM 610 $aLSTM-CRF model 610 $amedical applications 610 $amotion map 610 $amulti-label learning 610 $anatural language processing 610 $aobject detection network 610 $aobject recognition 610 $apedestrian attribute recognition 610 $aPOS syntactic rules 610 $aresource-efficient inference 610 $ascalability 610 $asentiment analysis 610 $asentiment attention mechanism 610 $aship identification 610 $atext recognition 610 $atooth-marked tongue 610 $aword embedding 615 7$aInformation technology industries 700 $aXibilia$b Maria Gabriella$4edt$01096523 702 $aGraziani$b Salvatore$4edt 702 $aXibilia$b Maria Gabriella$4oth 702 $aGraziani$b Salvatore$4oth 906 $aBOOK 912 $a9910557553903321 996 $aInnovative Topologies and Algorithms for Neural Networks$93018938 997 $aUNINA