124 Hits in 2.7 sec

Offline Contextual Bayesian Optimization for Nuclear Fusion [article]

Youngseog Chung, Ian Char, Willie Neiswanger, Kirthevasan Kandasamy, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
2020 arXiv   pre-print
Nuclear fusion is regarded as the energy of the future since it presents the possibility of unlimited clean energy.  ...  Since learning on a real world reactor is infeasible, we tackle this problem by attempting to learn optimal controls offline via a simulator, where the state of the plasma can be explicitly set.  ...  The authors would also like to thank the reviewers of the Machine Learning and the Physical Sciences workshop for their helpful feedback.  ... 
arXiv:2001.01793v1 fatcat:lmltya3xyjg3jf6n55itbpzgea

Dense RGB-D Semantic Mapping with Pixel-Voxel Neural Network

Cheng Zhao, Li Sun, Pulak Purkait, Tom Duckett, Rustam Stolkin
2018 Sensors  
That is, the PixelNet can learn the high-level contextual information from 2D RGB images, and the VoxelNet can learn 3D geometrical shapes from the 3D point cloud.  ...  In this paper, a novel Pixel-Voxel network is proposed for dense 3D semantic mapping, which can perform dense 3D mapping while simultaneously recognizing and labelling the semantic category each point  ...  Acknowledgments: We thank NVIDIA Corporation for generously donating a high-power TITAN X GPU. Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/s18093099 pmid:30223501 pmcid:PMC6164553 fatcat:oxcqwuu75vhmnkcbz6n5m6fxxe

Dense RGB-D semantic mapping with Pixel-Voxel neural network [article]

Cheng Zhao, Li Sun, Pulak Purkait, Rustam Stolkin
2017 arXiv   pre-print
For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features but also simultaneously  ...  Unlike the existing architecture that fuses score maps from different models with equal weights, we proposed a Softmax weighted fusion stack that adaptively learns the varying contributions of PixelNet  ...  All of those three methods require fully connected CRF [21] optimization as an offline post-processing, i.e., the best performance semantic mapping is not an online system. Zhao et al.  ... 
arXiv:1710.00132v3 fatcat:nqi5r47od5ddpjybfaszqxsunu

Reinforcement Learning in Practice: Opportunities and Challenges [article]

Yuxi Li
2022 arXiv   pre-print
Then we discuss challenges, in particular, 1) foundation, 2) representation, 3) reward, 4) exploration, 5) model, simulation, planning, and benchmarks, 6) off-policy/offline learning, 7) learning to learn  ...  Then we discuss opportunities of RL, in particular, products and services, games, bandits, recommender systems, robotics, transportation, finance and economics, healthcare, education, combinatorial optimization  ...  ., for healthcare, autonomous driving, and nuclear fusion. Thus off-policy/offline learning attract significant attention recently.  ... 
arXiv:2202.11296v2 fatcat:xdtsmme22rfpfn6rgfotcspnhy

Beyond Pinball Loss: Quantile Methods for Calibrated Uncertainty Quantification [article]

Youngseog Chung, Willie Neiswanger, Ian Char, Jeff Schneider
2021 arXiv   pre-print
We provide a thorough experimental evaluation of our methods, which includes a high dimensional uncertainty quantification task in nuclear fusion.  ...  In particular, we propose methods that can apply to any class of regression model, allow for selecting a trade-off between calibration and sharpness, optimize for calibration of centered intervals, and  ...  Offline contextual bayesian optimization for nuclear fusion. arXiv preprint arXiv:2001.01793, 2020. [12] Youngseog Chung, Ian Char, Han Guo, Jeff Schneider, and Willie Neiswanger.  ... 
arXiv:2011.09588v4 fatcat:amkf3pw5tbchxe77lju6ls6kw4

Towards low bit rate mobile visual search with multiple-channel coding

Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Yong Rui, Shih-Fu Chang, Wen Gao
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
Meanwhile, stepping forward from the state-of-the-art compact descriptor extractions, we exploit the rich contextual cues at the mobile end (such as GPS tags for mobile visual search and 2D barcodes or  ...  In this paper, we propose a multiple-channel coding scheme to extract compact visual descriptors for low bit rate mobile visual search.  ...  The MCVD consists of both offline learning and online extraction phases: Its offline learning involves learning an optimal channel division, as well as an optimal descriptor compression with respect to  ... 
doi:10.1145/2072298.2072372 dblp:conf/mm/JiDCYRCG11 fatcat:ir7dmmnitvg2fgdsitm376oqde

A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition

Cheng Zhao, Li Sun, Rustam Stolkin
2017 2017 18th International Conference on Advanced Robotics (ICAR)  
Enabling robots to recognise different materials (concrete, metal etc.) in a scene is important for many tasks, e.g. robotic interventions in nuclear decommissioning.  ...  To the best of our knowledge, this work is the first real-time end-to-end system for simultaneous 3D reconstruction and material recognition.  ...  But most such methods [6] [7] [8] rely on using fully connected CRF [15] optimization as an offline post-processing step, following online 3D reconstruction, i.e. these methods do not actually achieve  ... 
doi:10.1109/icar.2017.8023499 dblp:conf/icar/ZhaoSS17 fatcat:qrijis6borhopiykqa535tq35y

On the Use of Predictive Models for Improving the Quality of Industrial Maintenance: An Analytical Literature Review of Maintenance Strategies

Oana Merkt
2019 Proceedings of the 2019 Federated Conference on Computer Science and Information Systems  
Due to advances in machine learning techniques and sensor technology, the data driven perspective is nowadays the preferred approach for improving the quality of maintenance for machines and processes  ...  Our study reviews existing maintenance works by highlighting the main challenges and benefits and consequently, it shares recommendations and good practices for the appropriate usage of data analysis tools  ...  Our research work reviews the model-agnostic data fusion techniques in order to find solutions for their optimal usage.  ... 
doi:10.15439/2019f101 dblp:conf/fedcsis/Merkt19 fatcat:wmn7czw4njgivmjt5gr7ptn2ve

Machine Learning for Sustainable Energy Systems

Priya L. Donti, J. Zico Kolter
2021 Annual Review Environment and Resources  
Please see for revised estimates.  ...  In recent years, machine learning has proven to be a powerful tool for deriving insights from data.  ...  a cooperative agreement between the National Science Foundation and Carnegie • Machine Learning for Sustainable Energy Systems  ... 
doi:10.1146/annurev-environ-020220-061831 fatcat:pplsvl4zu5arngtbrov4uod74e

Practical Bayesian Optimization of Objectives with Conditioning Variables [article]

Michael Pearce, Janis Klaise, Matthew Groves
2020 arXiv   pre-print
Bayesian optimization is a class of data efficient model based algorithms typically focused on global optimization.  ...  Given partitions of CIFAR-10, we optimize CNN hyperparameters for each partition.  ...  Acknowledgements We would like to thank Ayman Boustati for helpful discussions and code review.  ... 
arXiv:2002.09996v2 fatcat:2ka2oupyira6lihyob4mb7gnji

Advancing Fusion with Machine Learning Research Needs Workshop Report

David Humphreys, A. Kupresanin, M. D. Boyer, J. Canik, C. S. Chang, E. C. Cyr, R. Granetz, J. Hittinger, E. Kolemen, E. Lawrence, V. Pascucci, A. Patra (+1 others)
2020 Journal of fusion energy  
and approaches for applying ML/AI methods to fusion energy research.  ...  Data-driven machine learning methods have also been applied to fusion energy research for over 2 decades, including significant advances in the areas of disruption prediction, surrogate model generation  ...  systems to optimize measurements for control; and the design of optimized trajectories and control algorithms. • Fusion Problem Elements For an economical fusion power plant, fusion gain Qdefined as  ... 
doi:10.1007/s10894-020-00258-1 fatcat:pzk3vza7v5eytbsrg2htkr5ujq

Condition-Based Maintenance—An Extensive Literature Review

Elena Quatrini, Francesco Costantino, Giulio Di Gravio, Riccardo Patriarca
2020 Machines  
Based on these considerations, data fusion levels remain relevant [51] -starting from signal-level fusion, including feature-level fusion up to decision-level fusion.  ...  An innovative mixed-integer optimization model for maintenance scheduling is proposed to rely on sensor-driven interventions, via a Bayesian prognostic model [206] .  ... 
doi:10.3390/machines8020031 fatcat:iwvbt5arqfditbreegovxww7te

Content-Based Medical Image Retrieval: A Survey of Applications to Multidimensional and Multimodality Data

Ashnil Kumar, Jinman Kim, Weidong Cai, Michael Fulham, Dagan Feng
2013 Journal of digital imaging  
These image collections offer the opportunity for evidence-based diagnosis, teaching, and research; for these applications, there is a requirement for appropriate methods to search the collections for  ...  We use these categories as a framework for discussing the state of the art, focusing on the characteristics and modalities of the information used during medical image retrieval.  ...  Acknowledgments We are grateful to our collaborators at the Royal Prince Alfred Hospital, Sydney, Australia for their direct and indirect contributions to this work.  ... 
doi:10.1007/s10278-013-9619-2 pmid:23846532 pmcid:PMC3824925 fatcat:5hasvmf7uncjtkpip4w4keea5m

Dynamic Target Tracking Method Based on Medical Imaging

Guofeng Qin, Jiahao Qin, Qiufang Xia, Jianghuang Zou, Pengpeng Lin, Chengkun Ren, Ruihan Wang
2022 Frontiers in Physiology  
The cross fusion of rehabilitation medicine and computer graphics is becoming a research hotspot.  ...  For the moving barium meal, the discrete point tracking and improved inter frame difference method are proposed; for the position calibration of tissues and organs, the Kernel Correlation Filter (KCF)  ...  Wang (2013) proposed a robust information fusion method that combines learning-based and conventional methods for fast and accurate detecting and tracking of deformable objects with various applications  ... 
doi:10.3389/fphys.2022.894282 fatcat:wsplbiqmjnhelmrt4lt276pooq

System-Level Predictive Maintenance: Review of Research Literature and Gap Analysis [article]

Kyle Miller, Artur Dubrawski
2020 arXiv   pre-print
actions, while reflecting increased monetary and safety costs for system failures.  ...  We differentiate the existing capabilities of condition estimation and failure risk forecasting as currently applied to simple components, from the capabilities needed to solve the same tasks for complex  ...  The authors divide metrics into offline and online measures. Offline metrics measure accuracy of RUL estimations or failure risks for example.  ... 
arXiv:2005.05239v1 fatcat:ipkagyvdwvd6hovk4swynmvpte
« Previous Showing results 1 — 15 out of 124 results