Naslov
Applications of generative approaches for artificial intelligence

Autori
Siniša Šegvić

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, pp prezentacija, stručni

Skup
AI2Future 2022

Mjesto i datum
Zagreb, Hrvatska, 13-14.10.2022

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Nije recenziran

Ključne riječi
computer vision

Sažetak
Most machine learning applications leverage discriminative models and supervised learning. However, discriminative models are unable to generate new content or measure plausibility of the data. Additionally, they are prone to learning simple decision rules which perform well on standard benchmarks but fail in real-world scenarios. Generative approaches are a promising approach towards alleviating these problems due to ability to learn complementary information from the training dataset. We are especially interested in a class of generative approaches that optimizes the data likelihood due to resistance to mode collapse. This presentation shall introduce prominent generative approaches and provide an overview of application fields in computer vision and natural language processing.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA