2 papers
cs.LG2024
Tighter Bounds on the Information Bottleneck with Application to Deep Learning
Nir Weingarten, Zohar Yakhini, Moshe Butman +1
Deep Neural Nets (DNNs) learn latent representations induced by their downstream task, objective function, and other parameters. The quality of the learned representations impacts…
cs.CL2022
Style transfer and classification in hebrew news items
Nir Weingarten
Hebrew is a Morphological rich language, making its modeling harder than simpler language. Recent developments such as Transformers in general and Bert in particular opened a path…