Abstract: Deep learning algorithms are notoriously data-hungry. However, in many sequential task domains, we have a limited amount of data. Thus, it is important to devise algorithms to select data samples optimally and...
Abstract: Deep learning algorithms are notoriously data-hungry. However, in many sequential task domains, we have a limited amount of data. Thus, it is important to devise algorithms to select data samples optimally and...
ast day of classes -Session Two; Summer Term ends - CPE SUMMER 2022
Last day of classes - UNIVERSITY SUMMER 2022
Abstract:
There are significant efforts to develop better neural approaches for information retrieval problems. However, the vast majority of these studies are conducted using English-only data. In fact, trends...
Abstract: Self-supervised large language models (LMs) have become a highly-influential and foundational tool for many NLP models. For this reason, their expressivity is an important topic of study. In near-universal...
Abstract: Neural image synthesis approaches have become increasingly popular over the last years due to their ability to generate photorealistic images useful for several applications, such as digital entertainment, mixed...
Abstract: Lack of data is almost always the cause of the suboptimal performance of neural networks. Even though data scarce scenarios can be simulated for any task by assuming limited access to training data, we study two...
All doctoral students are welcome to join in order to learn about the timelines and processes for submitting a synthesis project and portfolio.
Final grades due - UNIVERSITY SUMMER 2022
Remaining Summer grades due - CPE SUMMER 2022