Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Martin Wistuba"'
Autor:
Akihiro Kishimoto, Djallel Bouneffouf, Radu Marinescu, Parikshit Ram, Ambrish Rawat, Martin Wistuba, Paulito Palmes, Adi Botea
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:10228-10237
Optimizing a machine learning (ML) pipeline has been an important topic of AI and ML. Despite recent progress, pipeline optimization remains a challenging problem, due to potentially many combinations to consider as well as slow training and validati
Autor:
Radu Marinescu, Akihiro Kishimoto, Parikshit Ram, Ambrish Rawat, Martin Wistuba, Paulito P. Palmes, Adi Botea
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:8902-8911
AutoML automatically selects, composes and parameterizes machine learning algorithms into a workflow or pipeline of operations that aims at maximizing performance on a given dataset. Although current methods for AutoML achieved impressive results the
Autor:
Arunima Chaudhary, Alayt Issak, Kiran Kate, Yannis Katsis, Abel Valente, Dakuo Wang, Alexandre Evfimievski, Sairam Gurajada, Ban Kawas, Cristiano Malossi, Lucian Popa, Tejaswini Pedapati, Horst Samulowitz, Martin Wistuba, Yunyao Li
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:16001-16003
Building models for natural language processing (NLP) tasks remains a daunting task for many, requiring significant technical expertise, efforts, and resources. In this demonstration, we present AutoText, an end-to-end AutoAI framework for text, to l
Autor:
Hamza Ouarnoughi, Hadjer Benmeziane, Kaoutar El Maghraoui, Martin Wistuba, Naigang Wang, Smail Niar
Publikováno v:
Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}
Thirtieth International Joint Conference on Artificial Intelligence, Aug 2021, Montreal, Canada. pp.4322-4329, ⟨10.24963/ijcai.2021/592⟩
IJCAI
Thirtieth International Joint Conference on Artificial Intelligence, Aug 2021, Montreal, Canada. pp.4322-4329, ⟨10.24963/ijcai.2021/592⟩
IJCAI
International audience; There is no doubt that making AI mainstream by bringing powerful, yet power hungry deep neural networks (DNNs) to resource-constrained devices would required an efficient co-design of algorithms, hardware and software. The inc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f181376173073a4b8c53f902c965bb73
https://hal-uphf.archives-ouvertes.fr/hal-03379694
https://hal-uphf.archives-ouvertes.fr/hal-03379694
Autor:
Martin Wistuba
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783030676636
ECML/PKDD (3)
ECML/PKDD (3)
The term Neural Architecture Search (NAS) refers to the automatic optimization of network architectures for a new, previously unknown task. Since testing an architecture is computationally very expensive, many optimizers need days or even weeks to fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cc1f22d5fd5c0ee983b7748c86304575
https://doi.org/10.1007/978-3-030-67664-3_15
https://doi.org/10.1007/978-3-030-67664-3_15
Autor:
Alexander Gray, Ambrish Rawat, Martin Wistuba, Thanh Lam Hoang, Tejaswini Pedapati, Sijia Liu, Horst Samulowitz, Beat Buesser, Djallel Bouneffouf, Charu C. Aggarwal, Parikshit Ram, Udayan Khurana
Publikováno v:
IJCNN
Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it. This makes data science time consuming and restricted to experts with the resulting quality heavily dependent on their experience and skills. To
Publikováno v:
ICMR
The growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of methods to automate deep learning. The choice of network architecture has proven critical, and many improveme
Autor:
Ambrish Rawat, Martin Wistuba
Publikováno v:
Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461461
ECML/PKDD (2)
ECML/PKDD (2)
We introduce a new Large Margin Gaussian Process (LMGP) model by formulating a pseudo-likelihood for a generalised multi-class hinge loss. We derive a highly scalable training objective for the proposed model using variational-inference and inducing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db4ac4b971f8d611ba8a37443012cd37
https://doi.org/10.1007/978-3-030-46147-8_30
https://doi.org/10.1007/978-3-030-46147-8_30
Publikováno v:
Machine Learning. 107:43-78
Algorithm selection as well as hyperparameter optimization are tedious task that have to be dealt with when applying machine learning to real-world problems. Sequential model-based optimization (SMBO), based on so-called “surrogate models”, has b
Publikováno v:
IJCAI
We consider the stochastic multi-armed bandit problem and the contextual bandit problem with historical observations and pre-clustered arms. The historical observations can contain any number of instances for each arm, and the pre-clustering informat