Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Diana Benavides-Prado"'
Autor:
Shazia Sadiq, Amir Aryani, Gianluca Demartini, Wen Hua, Marta Indulska, Andrew Burton-Jones, Hassan Khosravi, Diana Benavides-Prado, Timos Sellis, Ida Someh, Rhema Vaithianathan, Sen Wang, Xiaofang Zhou
Publikováno v:
The VLDB Journal. 31:1059-1084
The appetite for effective use of information assets has been steadily rising in both public and private sector organisations. However, whether the information is used for social good or commercial gain, there is a growing recognition of the complex
Autor:
Kieran Elmes, Diana Benavides-Prado, Neşet Özkan Tan, Trung Bao Nguyen, Nicholas Sumpter, Megan Leask, Michael Witbrock, Alex Gavryushkin
Despite being the widely-used gold standard for linking common genetic variations to phenotypes and disease, genome-wide association studies (GWAS) suffer major limitations, partially attributable to the reliance on simple, typically linear, models o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0766bdac0d117cdb5e78cc1f745b43da
https://doi.org/10.1101/2022.07.07.499217
https://doi.org/10.1101/2022.07.07.499217
Autor:
Joshua Bensemann, Alex Peng, Diana Benavides-Prado, Yang Chen, Neset Tan, Paul Michael Corballis, Patricia Riddle, Michael Witbrock
Publikováno v:
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics.
Publikováno v:
Journal of Artificial Intelligence Research. 68:159-224
Learning a sequence of tasks is a long-standing challenge in machine learning. This setting applies to learning systems that observe examples of a range of tasks at different points in time. A learning system should become more knowledgeable as more
Publikováno v:
IJCNN
Catastrophic forgetting is an issue for all continual learning models with neural network architectures, however, research in this area often concentrates on prevention of catastrophic forgetting and not on the potential to improve existing knowledge
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030863395
ICANN (2)
ICANN (2)
In control systems applications, controllers for different plants are usually designed with different methods. Although plants may share common characteristics, these controllers are generally designed in isolation. The problem of continually learnin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::264135f0c3ec4aba5a0a349a3f17a33b
https://doi.org/10.1007/978-3-030-86340-1_32
https://doi.org/10.1007/978-3-030-86340-1_32
This book constitutes the proceedings of the 21st Australasian Conference on Data Science and Machine Learning, AusDM 2023, held in Auckland, New Zealand, during December 11–13, 2023.The 20 full papers presented in this book were carefully reviewed
Publikováno v:
IJCNN
Selective transfer has been proposed as an alternative for transferring fragments of knowledge. Previous work showed that transferring selectively from a group of hypotheses helps to speed learning on a target task. Similarly, existing hypotheses cou
Autor:
Rachel P. Berger, Emily Putnam-Hornstein, Rhema Vaithianathan, Alexandra Chouldechova, Diana Benavides-Prado
Publikováno v:
JAMA Pediatrics. 174:e202770
Importance Nearly 6 million children are reported as allegedly experiencing abuse or neglect in the US annually. Child protection agencies are increasingly turning to automated predictive risk models (PRMs) that mine information found in routinely co
Autor:
Diana Benavides-Prado
Publikováno v:
AAAI
In our research, we study the problem of learning a sequence of supervised tasks. This is a long-standing challenge in machine learning. Our work relies on transfer of knowledge between hypotheses learned with Support Vector Machines. Transfer occurs