https://wiki.mindmaker.it/index.php?action=history&feed=atom&title=Deep_Convolutional_Neural_Networks_%28AlexNet%29 2026-05-01T12:36:34Z Cronologia della pagina su questo sito MediaWiki 1.41.0 https://wiki.mindmaker.it/index.php?title=Deep_Convolutional_Neural_Networks_(AlexNet)&diff=2509&oldid=prev 2024-08-17T10:38:10Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="it"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Versione meno recente</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Versione delle 10:38, 17 ago 2024</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1">Riga 1:</td> <td colspan="2" class="diff-lineno">Riga 1:</td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">Titolo</del>: <del style="font-weight: bold; text-decoration: none;">[[Titolo::Deep Convolutional Neural Networks (AlexNet)]]</del></div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">{{template pubblicazione</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">|data=2012</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">|autori=Yong-Deok Kim, Eunhyeok Park, S. Yoo, Taelim Choi, Lu Yang, Dongjun Shin</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">|URL=https</ins>:<ins style="font-weight: bold; text-decoration: none;">//www.semanticscholar.org/paper/4ca3b996d888d7178dbbf9855bb2ab253bdfa43d</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">|topic=Compressione di Reti Neurali</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">|citazioni=844</ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">}}</ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">URL</del>: <del style="font-weight: bold; text-decoration: none;">[[URL::https://d2l</del>.<del style="font-weight: bold; text-decoration: none;">ai/chapter_convolutional</del>-<del style="font-weight: bold; text-decoration: none;">modern/alexnet</del>.<del style="font-weight: bold; text-decoration: none;">html]]</del></div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Questo articolo presenta un metodo per comprimere le reti neurali convoluzionali profonde (CNN) al fine di renderle più efficienti per l'esecuzione su dispositivi mobili. Il metodo proposto, chiamato "one-shot whole network compression", si compone di tre fasi</ins>: <ins style="font-weight: bold; text-decoration: none;">selezione del rango con fattorizzazione matriciale variazionale bayesiana, decomposizione di Tucker sul tensore del kernel e fine-tuning per recuperare la perdita di accuratezza accumulata</ins>. <ins style="font-weight: bold; text-decoration: none;">Gli autori dimostrano l'efficacia del loro metodo comprimendo diverse CNN (AlexNet, VGGS, GoogLeNet e VGG</ins>-<ins style="font-weight: bold; text-decoration: none;">16) e testandole su smartphone. I risultati mostrano significative riduzioni delle dimensioni del modello, del tempo di esecuzione e del consumo energetico, a fronte di una piccola perdita di accuratezza. L'articolo affronta anche l'importante questione dell'implementazione della convoluzione 1x1, un'operazione chiave del modulo inception di GoogLeNet e delle CNN compresse dal metodo proposto</ins>.</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div> </div></td><td colspan="2" class="diff-side-added"></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">[[Category:pubblicazione]]</del></div></td><td colspan="2" class="diff-side-added"></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div> </div></td><td colspan="2" class="diff-side-added"></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">__SHOWFACTBOX__</del></div></td><td colspan="2" class="diff-side-added"></td></tr> </table>

Mindmakerbot https://wiki.mindmaker.it/index.php?title=Deep_Convolutional_Neural_Networks_(AlexNet)&diff=2001&oldid=prev 2024-04-10T10:24:13Z

<p>Creata pagina con &quot;Titolo: <a href="/index.php?title=Titolo::Deep_Convolutional_Neural_Networks_(AlexNet)&amp;action=edit&amp;redlink=1" class="new" title="Titolo::Deep Convolutional Neural Networks (AlexNet) (la pagina non esiste)">Titolo::Deep Convolutional Neural Networks (AlexNet)</a> URL: <a href="/index.php?title=URL::https://d2l.ai/chapter_convolutional-modern/alexnet.html&amp;action=edit&amp;redlink=1" class="new" title="URL::https://d2l.ai/chapter convolutional-modern/alexnet.html (la pagina non esiste)">URL::https://d2l.ai/chapter_convolutional-modern/alexnet.html</a> <a href="/index.php/Categoria:Pubblicazione" title="Categoria:Pubblicazione">Category:pubblicazione</a> __SHOWFACTBOX__&quot;</p> <p><b>Nuova pagina</b></p><div>Titolo: [[Titolo::Deep Convolutional Neural Networks (AlexNet)]]<br /> <br /> URL: [[URL::https://d2l.ai/chapter_convolutional-modern/alexnet.html]]<br /> <br /> [[Category:pubblicazione]]<br /> <br /> __SHOWFACTBOX__</div>

Sara Maserati