Machine learningDeep learning / NLP / CV

Semi-supervised Variational Autoencoder (M1/M2 Generative Model)

Uwekaji lebo mwingi ni ghali, kwa hivyo hifadhi za data mara nyingi huwa na mifano mingi zaidi isiyo na lebo kuliko iliyo na lebo. Kiainishaji cha kawaida hutupa data isiyo na lebo. VAE yenye usimamizi nusu badala yake huchukulia lebo ya nukta isiyo na lebo kama kigezo kingine fiche cha kugharamia, na hufunza mwanamitindo wa kuzalisha (dekoda) na mtandao wa kutambua (enkoda pamoja na kiainishaji) pamoja. Kwa sababu mwanamitindo lazima urejeshe pembejeo kila moja iwe na lebo au la, mifano isiyo na lebo huathiri kikamilifu uwakilishi uliojifunzwa, ikiboresha uainishaji kwa viwango vya chini sana vya lebo.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

Semi-supervised Variational Autoencoder

Mtandao wa Kushawishi un…Variational Autoencoder…Mtandao wa Mawasiliano w…Transformer yenye usimam…Transfer learning variat…Variational Autoencoder

Vyanzo

Kingma, D. P., Mohamed, S., Rezende, D. J., & Wierstra, D. (2014). Semi-supervised learning with deep generative models. Advances in Neural Information Processing Systems (NeurIPS), 27, 3581–3589. link ↗
Kingma, D. P., & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR 2014). link ↗

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Semi-supervised Variational Autoencoder (M1/M2 Generative Model). ScholarGate. https://scholargate.app/sw/deep-learning/semi-supervised-variational-autoencoder

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Mtandao wa Kushawishi unaozalisha (Generative Adversarial Network - GAN)Ujifunzaji wa Kina↔ compare
Variational Autoencoder ya Kujisimamia YenyeweUjifunzaji wa Kina↔ compare
Mtandao wa Mawasiliano wa Nusu-UsindikajiUjifunzaji wa Kina↔ compare
Transformer yenye usimamizi-nusuUjifunzaji wa Kina↔ compare
Transfer learning variational autoencoderUjifunzaji wa Kina↔ compare
Variational AutoencoderUjifunzaji wa Kina↔ compare

Compare side by side →

Imerejelewa na

Variational Autoencoder ya Kujisimamia Yenyewe Transfer learning variational autoencoder

Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →