Zobrazeno 1 - 10
of 2 725
pro vyhledávání: '"Zecevic, A"'
Autor:
Dycke, Nils, Zečević, Matej, Kuznetsov, Ilia, Suess, Beatrix, Kersting, Kristian, Gurevych, Iryna
Diagnostic reasoning is a key component of expert work in many domains. It is a hard, time-consuming activity that requires expertise, and AI research has investigated the ways automated systems can support this process. Yet, due to the complexity of
Externí odkaz:
http://arxiv.org/abs/2409.05367
$\chi$SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
Autor:
Poonia, Harsh, Willig, Moritz, Yu, Zhongjie, Zečević, Matej, Kersting, Kristian, Dhami, Devendra Singh
Causal inference in hybrid domains, characterized by a mixture of discrete and continuous variables, presents a formidable challenge. We take a step towards this direction and propose Characteristic Interventional Sum-Product Network ($\chi$SPN) that
Externí odkaz:
http://arxiv.org/abs/2408.07545
Autor:
Donelle, Lorie, Regan, Sandra, Kerr, Michael, Zwarenstein, Merrick, Bauer, Michael, Warner, Grace, Isaranuwatchai, Wanrudee, Zecevic, Aleksandra, Borycki, Elizabeth, Forbes, Dorothy, Weeks, Lori, Leipert, Bev, Read, Emily
Publikováno v:
JMIR Research Protocols, Vol 9, Iss 1, p e15027 (2020)
BackgroundSignificant chronic disease challenges exist among older adults. However, most older adults want to remain at home even if their health conditions challenge their ability to live independently. Yet publicly funded home care resources are sc
Externí odkaz:
https://doaj.org/article/dc46c5a8ea7b4ef98471b7ea2692aff9
Structural causal models (SCMs) are a powerful tool for understanding the complex causal relationships that underlie many real-world systems. As these systems grow in size, the number of variables and complexity of interactions between them does, too
Externí odkaz:
http://arxiv.org/abs/2310.08377
Autor:
Agathe Zecevic, Laurence Jackson, Xinyue Zhang, Polychronis Pavlidis, Jason Dunn, Nigel Trudgill, Shahd Ahmed, Pierfrancesco Visaggi, Zanil YoonusNizar, Angus Roberts, Sebastian S. Zeki
Publikováno v:
npj Digital Medicine, Vol 7, Iss 1, Pp 1-9 (2024)
Abstract Manual decisions regarding the timing of surveillance endoscopy for premalignant Barrett’s oesophagus (BO) is error-prone. This leads to inefficient resource usage and safety risks. To automate decision-making, we fine-tuned Bidirectional
Externí odkaz:
https://doaj.org/article/21c95731d5ee42b9b99fc5f106700837
Publikováno v:
Transactions in Machine Learning Research (08/2023)
Some argue scale is all what is needed to achieve AI, covering even causal models. We make it clear that large language models (LLMs) cannot be causal and give reason onto why sometimes we might feel otherwise. To this end, we define and exemplify a
Externí odkaz:
http://arxiv.org/abs/2308.13067
We present the TherapyView, a demonstration system to help therapists visualize the dynamic contents of past treatment sessions, enabled by the state-of-the-art neural topic modeling techniques to analyze the topical tendencies of various psychiatric
Externí odkaz:
http://arxiv.org/abs/2302.10845
This short paper discusses continually updated causal abstractions as a potential direction of future research. The key idea is to revise the existing level of causal abstraction to a different level of detail that is both consistent with the history
Externí odkaz:
http://arxiv.org/abs/2212.12575
Many researchers have voiced their support towards Pearl's counterfactual theory of causation as a stepping stone for AI/ML research's ultimate goal of intelligent systems. As in any other growing subfield, patience seems to be a virtue since signifi
Externí odkaz:
http://arxiv.org/abs/2212.12570
Autor:
Didi, Kieran, Zečević, Matej
Research around AI for Science has seen significant success since the rise of deep learning models over the past decade, even with longstanding challenges such as protein structure prediction. However, this fast development inevitably made their flaw
Externí odkaz:
http://arxiv.org/abs/2212.12560