74 Hits in 4.8 sec

Towards the decathlon challenge of search heuristics

Edmund K. Burke, Tim Curtois, Graham Kendall, Matthew Hyde, Gabriela Ochoa, Jose A. Vazquez-Rodriguez
2009 Proceedings of the 11th annual conference companion on Genetic and evolutionary computation conference - GECCO '09  
Using an Olympic metaphor, we are not solely focussed on the 100 meters race, but instead on the decathlon of modern search methodologies. Categories  ...  We present an object oriented framework for designing and evaluating heuristic search algorithms that achieve a high level of generality and work well on a wide range of combinatorial optimization problems  ...  Our goal is to promote research into generally applicable search methodologies and eventually conduct the Decathlon challenge of search heuristics.  ... 
doi:10.1145/1570256.1570303 dblp:conf/gecco/BurkeCKHOV09 fatcat:qr2phvkxf5dafdwx4yimlotc4q

Iterated local search vs. hyper-heuristics: Towards general-purpose search algorithms

Edmund Burke, Tim Curtois, Matthew Hyde, Graham Kendall, Gabriela Ochoa, Sanja Petrovic, Jose A. Vazquez-Rodriguez, Michel Gendreau
2010 IEEE Congress on Evolutionary Computation  
An important challenge within hyper-heuristic research is to design search methodologies that work well, not only across different instances of the same problem, but also across different problem domains  ...  The study is intended as a proof of concept of the proposed interface and domain modules, as a benchmark for testing the generalisation abilities of heuristic search algorithms.  ...  challenge of search heuristics.  ... 
doi:10.1109/cec.2010.5586064 dblp:conf/cec/BurkeCHKOPRG10 fatcat:p5gne5fuordndhjokcyhzohah4

Automated Design of Deep Learning Methods for Biomedical Image Segmentation [article]

Fabian Isensee, Paul F. Jäger, Simon A. A. Kohl, Jens Petersen, Klaus H. Maier-Hein
2020 arXiv   pre-print
Biomedical imaging is a driver of scientific discovery and core component of medical care, currently stimulated by the field of deep learning.  ...  Without manual tuning, nnU-Net surpasses most specialised deep learning pipelines in 19 public international competitions and sets a new state of the art in the majority of the 49 tasks.  ...  Acknowledgements This work was co-funded by the National Center for Tumor Diseases (NCT) in Heidelberg and the Helmholtz Imaging Platform (HIP) of the German Cancer Consortium (DKTK).  ... 
arXiv:1904.08128v2 fatcat:km56vthsonadtgpsj4h356ofk4

Accelerating progress in Artificial General Intelligence: Choosing a benchmark for natural world interaction

Brandon Rohrer
2010 Journal of Artificial General Intelligence  
The paper concludes with a description of a task that might be included in the AGI battery: the search and retrieve task.  ...  The AGI battery is designed to be appropriate to the capabilities of currently existing systems. Both the direction task and the AGI battery would require further definition before implementing.  ...  Sandia is a multiprogram laboratory operated by Sandia Corporation, a Lockheed Martin Company, for the United States Department of Energys National Nuclear Security Administration under Contract DE-AC04  ... 
doi:10.2478/v10229-011-0005-5 fatcat:waeis6nbpjdn7oxgcy76u5q4iu

Hyper-heuristics: a survey of the state of the art

Edmund K Burke, Michel Gendreau, Matthew Hyde, Graham Kendall, Gabriela Ochoa, Ender Özcan, Rong Qu
2013 Journal of the Operational Research Society  
The distinguishing feature of hyper-heuristics is that they operate on a search space of heuristics (or heuristic components) rather than directly on the search space of solutions to the underlying problem  ...  Hyper-heuristics comprise a set of approaches that are motivated (at least in part) by the goal of automating the design of heuristic methods to solve hard computational search problems.  ...  The challenge is analogous to the athletics Decathlon event, where the goal is not to excel in one event at the expense of others, but to have a good general performance on each.  ... 
doi:10.1057/jors.2013.71 fatcat:wgusktpk4fau3lg22smrby4k4y

Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights [article]

Linus Ericsson, Henry Gouk, Timothy M. Hospedales
2020 arXiv   pre-print
Our method, BetaDataWeighter is evaluated using the popular self-supervised rotation prediction task on STL-10 and Visual Decathlon.  ...  In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available.  ...  (grant EP/L016427/1) and the University of Edinburgh.  ... 
arXiv:2006.12360v1 fatcat:ugbagavplbe77popjulddxcohi

HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet [article]

Cheng Peng, Andriy Myronenko, Ali Hatamizadeh, Vish Nath, Md Mahfuzur Rahman Siddiquee, Yufan He, Daguang Xu, Rama Chellappa, Dong Yang
2022 arXiv   pre-print
Our method is evaluated on public datasets from the Medical Segmentation Decathlon (MSD) challenge, and achieves SOTA performances.  ...  Semantic segmentation of 3D medical images is a challenging task due to the high variability of the shape and pattern of objects (such as organs or tumors).  ...  Finally, HyperSeg-NAS achieves new SOTA performance on multiple tasks in the Medical Segmentation Decathlon (MSD) challenge [1] using similar computing budget as DiNTS.  ... 
arXiv:2112.10652v2 fatcat:mtzdseug6fe6plhvyfqo2whkya

Multi-task learning for natural language processing in the 2020s: where are we going?

Joseph Worsham, Jugal Kalita
2020 Pattern Recognition Letters  
the release of new challenge problems, such as GLUE and the NLP Decathlon (decaNLP).  ...  This paper strives to provide a comprehensive survey of the numerous recent MTL contributions to the field of natural language processing and provide a forum to focus efforts on the hardest unsolved problems  ...  This acts as a good search heuristic for finding optimized task sets.  ... 
doi:10.1016/j.patrec.2020.05.031 fatcat:duze6ovk5fauxfn6vsbn5bgrbq

Metacognition, states of mind, cognitive biases, and interpersonal cycles: Proposal for an integrated narcissism model

Giancarlo Dimaggio, Antonio Semerari, Maurizio Falcone, Giuseppe Nicolò, Antonino Carcione, Michele Procacci
2002 Journal of psychotherapy integration  
After that we propose a psychopathological model describing the hierarchies of importance between the various dys-  ...  In this work the authors propose an integrated model that describes how the disorder perpetuates itself and suggest some hierarchies of importance between the elements portrayed above.  ...  of principle or the need for an intellectual challenge.  ... 
doi:10.1037/1053-0479.12.4.421 fatcat:ts7u63hpivgahjc76p5cjtajx4

Applying the Post-digital Strategy of Anexact Architecture to Non-standard Design Practices within the Challenging Construction Contexts

Sining Wang, Dandan Lin
2022 Heliyon  
The demonstrator projects are discussed based on the combination of the Participatory Action Research method and the idea of anexact architecture.  ...  Named 'anexact architecture', the post-digital design practice strategy presents a convergent diagram of seeking the feasible design solution space.  ...  Acknowledgements The authors acknowledge the students and faculty members from Soochow University and Technical University of Denmark for their support in the design and construction of Aurora.  ... 
doi:10.1016/j.heliyon.2022.e09982 fatcat:yl6ygrizenaevgocakppccndum

Integrated shallow and deep parsing

Anette Frank, Markus Becker, Berthold Crysmann, Bernd Kiefer, Ulrich Schäfer
2003 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03  
Our annotation-based method for dovetailing shallow and deep phrasal constraints is highly flexible, allowing targeted and fine-grained guidance of constraint-based parsing.  ...  Mediated by an XML-based multi-layer annotation architecture, we interleave a robust, but accurate stochastic topological field parser of German with a constraintbased HPSG parser.  ...  In particular, we want to use analyses delivered by an efficient shallow parser to pre-structure the search space of HPSG parsing, thereby enhancing its efficiency, and guiding deep parsing towards a best-first  ... 
doi:10.3115/1075096.1075110 dblp:conf/acl/FrankBCKS03 fatcat:b2yapvytlrgyrd5b3owrf4n2c4

Vol. 2 n. 3 | 2017 | SPECIAL ISSUE | FULL ISSUE

Luisa Bravo
2017 The Journal of Public Space  
Acknowledgments This research was supported by the Creative Arts Faculty Research Fund of the University of Auckland.  ...  I thank my colleagues of the School of Architecture and Planning who provided insight and expertise that greatly assisted the research.  ...  Changing the curriculum in order to fit the very different requirements of the Solar Decathlon is therefore part of the challenge, where a large group of students are required to work continuously and  ... 
doi:10.5204/jps.v2i3.128 fatcat:wjkhilcu6vgvzayoauzszwuy3u

Reports of the Workshops of the Thirty-First AAAI Conference on Artificial Intelligence

Monica Anderson, Roman Barták, John S. Brownstein, David L. Buckeridge, Hoda Eldardiry, Christopher Geib, Maria Gini, Aaron Isaksen, Sarah Keren, Robert Laddaga, Viliam Lisy, Rodney Martin (+25 others)
2017 The AI Magazine  
This report contains summaries of 12 of the workshops, and brief abstracts of the remaining 5  ...  The AAAI-17 workshop program included 17 workshops covering a wide range of topics in AI.  ...  toward a specific application.  ... 
doi:10.1609/aimag.v38i3.2755 fatcat:jomv3ziyujdjfmv5prhp5fsemy

Meta-Learning in Neural Networks: A Survey [article]

Timothy Hospedales, Antreas Antoniou, Paul Micaelli, Amos Storkey
2020 arXiv   pre-print
We then propose a new taxonomy that provides a more comprehensive breakdown of the space of meta-learning methods today.  ...  The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years.  ...  The search space is hard to define, and optimize. This is because most search spaces are broad, and the space of architectures is not trivially differentiable.  ... 
arXiv:2004.05439v2 fatcat:3r23tsxxkfbgzamow5miglkrye

Rationality and Charity

Paul Thagard, Richard E. Nisbett
1983 Philosophy of Science  
After comparing principles of charity of different degrees of severity, we argue that the stronger principles are likely to block understanding of human behavior and impede progress toward improving it  ...  It is necessary first to state the problem more clearly, by carefully formulating the relevant notions of rationality and the content of principles of charity.  ...  , then to use the operation of this heuristic as part of an explanation of the system's behavior.  ... 
doi:10.1086/289108 fatcat:niigxb2vpvehvldkrnvvibn3o4
« Previous Showing results 1 — 15 out of 74 results