Galleria
Playlist immagini
Gruppi
Unisciti a un gruppo
Acquisizione
Nuovo oggetto
Mappe concettuali
Gestione
Tabelle (CRUD generico)
Ricerca tag
Elaborazioni
Somma di prova
Sistema
Impostazioni
Esci
☰
Oggetti
LOGISTAR
LMP
ospite
⋮
Profilo utente
Preferenze colonne
Guida programma
Segnala anomalia
Cambia utente
⌂
💾 Salva
↻ Aggiorna
☑ Lista
🏷 Righe
Id
Descrizione
dta reg (aaaa-mm-gg)
Body
<p> </p> <p class="ContentParagraph ContentParagraph_align_left" data-testid="content-paragraph"><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text">AI researchers from Stanford and Turing award winner Yoshua Bengio have trained a large language model on human genome data to better predict DNA profiles.</span></p> <p class="ContentParagraph ContentParagraph_align_left" data-testid="content-paragraph"><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text">Researchers created </span><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text"><a class="ContentText-BodyTextChunk ContentText-BodyTextChunk_link" href="https://huggingface.co/papers/2306.15794" target="_blank" data-feathr-click-track="true" data-feathr-link-aids="["64db786b15f34666fc299753"]">HyenaDNA </a></span><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text">by combining the </span><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text"><a class="ContentText-BodyTextChunk ContentText-BodyTextChunk_link" href="https://arxiv.org/abs/2302.10866" target="_blank" data-feathr-click-track="true" data-feathr-link-aids="["64db786b15f34666fc299753"]">Hyena large language model</a></span><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text"> and pre-training it on human reference genomic sequences of up to one million tokens. Prior models have typically used context lengths of 512 to 4,000 token, or less than 0.001% of the human genome.</span></p> <p class="ContentParagraph ContentParagraph_align_left" data-testid="content-paragraph"><span class="ContentText ContentText_variant_bodyNormal" data-testid="content-text">Stanford’s researchers contend that most of the work on long context models have focused on natural language and code and that biology is “inherently made of ultralong sequences.”</span></p>
tipo ogg.
cat
subcat
proprietario
azienda
ute
selez1
op1
codart
codice
codclifor
motivo
url
email
tag
imgsrc
sunto_breve
sunto_medio
note
codice articolo analisi intervista (52.0%), algoritmo articolo analisi intervista ricerca (51.6%), text (50.9%), text_classification (50.4%), language_model (50.3%), linguaggio (48.7%), embedding (45.7%), text_generation (45.0%), machine learning (44.8%), dataset (44.7%), deep learning (44.4%), data_quality (43.7%), text_mining (43.7%), text_to_speech (43.2%), cognitive (42.7%), analisi (42.6%), training (42.0%), model_training (41.7%), datasource (41.6%), benchmark (41.3%)
keyscrape
Lista tag dell'oggetto (oggettag)
cod_tag
value
dev
5
gen
5
genoma
5
gpt
5
llm
5
nn
5
tool
5
wpg
5
Lista delle righe dell'oggetto (oggettir)
tip_pro
cod_pro
descrizione
val_pro
pes_pro
WBK
LLM
LLM
---.