Zobrazeno 1 - 10
of 1 438
pro vyhledávání: '"P. Dobbie"'
Causal structure discovery methods are commonly applied to structured data where the causal variables are known and where statistical testing can be used to assess the causal relationships. By contrast, recovering a causal structure from unstructured
Externí odkaz:
http://arxiv.org/abs/2410.06392
Deep neural networks can obtain impressive performance on various tasks under the assumption that their training domain is identical to their target domain. Performance can drop dramatically when this assumption does not hold. One explanation for thi
Externí odkaz:
http://arxiv.org/abs/2410.06349
Despite impressive performance on language modelling and complex reasoning tasks, Large Language Models (LLMs) fall short on the same tasks in uncommon settings or with distribution shifts, exhibiting a lack of generalisation ability. By contrast, sy
Externí odkaz:
http://arxiv.org/abs/2402.02636
Autor:
Gendron, Gaël, Chen, Yang, Rogers, Mitchell, Liu, Yiping, Azhar, Mihailo, Heidari, Shahrokh, Valdez, David Arturo Soriano, Knowles, Kobe, O'Leary, Padriac, Eyre, Simon, Witbrock, Michael, Dobbie, Gillian, Liu, Jiamou, Delmas, Patrice
Better understanding the natural world is a crucial task with a wide range of applications. In environments with close proximity between humans and animals, such as zoos, it is essential to better understand the causes behind animal behaviour and wha
Externí odkaz:
http://arxiv.org/abs/2312.14333
The benefits and capabilities of pre-trained language models (LLMs) in current and future innovations are vital to any society. However, introducing and using LLMs comes with biases and discrimination, resulting in concerns about equality, diversity
Externí odkaz:
http://arxiv.org/abs/2312.01509
The performance of machine learning models depends on the quality of the underlying data. Malicious actors can attack the model by poisoning the training data. Current detectors are tied to either specific data types, models, or attacks, and therefor
Externí odkaz:
http://arxiv.org/abs/2310.16224
Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant threats. In l
Externí odkaz:
http://arxiv.org/abs/2310.10744
Autor:
Hu, Hongsheng, Zhang, Xuyun, Salcic, Zoran, Sun, Lichao, Choo, Kim-Kwang Raymond, Dobbie, Gillian
Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known that FL ca
Externí odkaz:
http://arxiv.org/abs/2310.00222
Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has raised con
Externí odkaz:
http://arxiv.org/abs/2309.08624
Autor:
Steffen Albrecht, David Broderick, Katharina Dost, Isabella Cheung, Nhung Nghiem, Milton Wu, Johnny Zhu, Nooriyan Poonawala-Lohani, Sarah Jamison, Damayanthi Rasanathan, Sue Huang, Adrian Trenholme, Alicia Stanley, Shirley Lawrence, Samantha Marsh, Lorraine Castelino, Janine Paynter, Nikki Turner, Peter McIntyre, Patricia Riddle, Cameron Grant, Gillian Dobbie, Jörg Simon Wicker
Publikováno v:
BMC Medical Informatics and Decision Making, Vol 24, Iss 1, Pp 1-16 (2024)
Abstract Background Forecasting models predicting trends in hospitalization rates have the potential to inform hospital management during seasonal epidemics of respiratory diseases and the associated surges caused by acute hospital admissions. Hospit
Externí odkaz:
https://doaj.org/article/bc4496c0b482406da57fbcd3677319ef
