https://wiki.mindmaker.it/index.php?action=history&feed=atom&title=Long_Short-Term_Memory 2026-05-14T23:23:48Z Cronologia della pagina su questo sito MediaWiki 1.41.0 https://wiki.mindmaker.it/index.php?title=Long_Short-Term_Memory&diff=3090&oldid=prev 2024-09-09T04:56:27Z

<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 04:56, 9 set 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;">[[Categoria</del>:<del style="font-weight: bold; text-decoration: none;">Pubblicazione]]</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=1997</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=Sepp Hochreiter, J. Schmidhuber</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/2e9d221c206e9503ceb452302d68d10e293f2a10</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=Reti Neurali Ricorrenti</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=80233</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 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> </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;">L'apprendimento per memorizzare informazioni su intervalli di tempo estesi tramite backpropagation ricorrente richiede molto tempo, soprattutto a causa di un flusso di errore insufficiente e in decadimento. Questo articolo introduce un metodo nuovo, efficiente e basato sul gradiente chiamato memoria a breve e lungo termine (LSTM). Troncando il gradiente dove questo non fa male, LSTM può imparare a colmare ritardi minimi superiori a 1000 passi temporali discreti imponendo un flusso di errore costante attraverso carosello di errore costanti all'interno di unità speciali. Le unità gate moltiplicative imparano ad aprire e chiudere l'accesso al flusso di errore costante. LSTM è locale nello spazio e nel tempo; la sua complessità computazionale per passo temporale e peso è O(1).</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> </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;">{{#seo:</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;">            |title=Long Short-Term Memory</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;">            |title_mode=append</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;">            |keywords=rete neurale, apprendimento automatico, intelligenza artificiale, memoria a breve termine, memoria a lungo termine, backpropagation, gradiente, LSTM, intervalli di tempo, elaborazione del linguaggio naturale</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;">            |description=Questo articolo introduce la memoria a breve e lungo termine (LSTM), un metodo efficiente per addestrare reti neurali ricorrenti. LSTM risolve il problema del decadimento del gradiente troncandolo selettivamente, consentendo di apprendere dipendenze a lungo termine. Questo ha aperto la strada a significativi progressi nell'apprendimento automatico.</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> </table>

Mindmakerbot https://wiki.mindmaker.it/index.php?title=Long_Short-Term_Memory&diff=3089&oldid=prev 2024-09-09T04:56:05Z

<p>Creata pagina con &quot;<a href="/index.php/Categoria:Pubblicazione" title="Categoria:Pubblicazione">Categoria:Pubblicazione</a>&quot;</p> <p><b>Nuova pagina</b></p><div>[[Categoria:Pubblicazione]]</div>

Alesaccoia