Filters








3,577 Hits in 8.1 sec

A Review on Plastic Artificial Neural Networks: Exploring the Intersection between Neural Architecture Search and Continual Learning [article]

Mohamed Shahawy, Elhadj Benkhelifa, David White
2022 arXiv   pre-print
This study is the first extensive review on the intersection between AutoML and CL, outlining research directions for the different methods that can facilitate full automation and lifelong plasticity in  ...  The current state of the art on adaptive ANNs is still a premature area of research; nevertheless, Neural Architecture Search (NAS), a form of AutoML, and Continual Learning (CL) have recently gained an  ...  systems on learning and episodic memory [14] .  ... 
arXiv:2206.05625v1 fatcat:w32ni2t4irhl5hhwc2v4nm3bja

Partial hyperplane activation for generalized intersection cuts [article]

Aleksandr M. Kazachkov, Selvaprabu Nadarajah, Egon Balas, François Margot
2018 arXiv   pre-print
Our findings shed light on the the strengths of the PHA approach as well as suggest properties related to strong cuts that can be targeted in the future.  ...  We computationally evaluate these ideas in the COIN-OR framework on MIPLIB instances.  ...  The machine used is a shared 64bit PowerEdge R515 with 48GB of memory and twelve AMD Opteron 4176 processors clocked at 2.4GHz.  ... 
arXiv:1703.02221v2 fatcat:ce33d7vjvzbuxlxiubyyhay7si

Distributed Seams for Gigapixel Panoramas

Sujin Philip, Brian Summa, Julien Tierny, Peer-Timo Bremer, Valerio Pascucci
2015 IEEE Transactions on Visualization and Computer Graphics  
It shows near-perfect scaling on symmetric multiprocessing systems and good scaling on clusters and distributed shared memory systems.  ...  In this paper, we present a parallel, out-of-core seam computing technique that is fast, has small memory footprint, and is capable of running efficiently on different types of parallel systems.  ...  The cache sizes were configured based on the amount of memory available in the corresponding systems. All three systems are shared machines.  ... 
doi:10.1109/tvcg.2014.2366128 pmid:26357067 fatcat:ri3n7jhzvbfr3butrxxq2jwz2y

Accelerating Clique Counting in Sparse Real-World Graphs via Communication-Reducing Optimizations [article]

Amogh Lonkar, Scott Beamer
2021 arXiv   pre-print
We accelerate the counting phase with our reorganized subgraph data structures that reduce memory traffic to improve scaling bottlenecks.  ...  Of the ordering-based algorithms, kClist is the state-of-the art algorithm designed to work on sparse real-world graphs.  ...  In contrast, our approach skips the remapping and simply appends each vertex's common neighbors to the end of the array.  ... 
arXiv:2112.10913v2 fatcat:fdhml5ywoza75bbhdxjoa4bfjq

Tracking Structure of Streaming Social Networks

David Ediger, Jason Riedy, David A. Bader, Henning Meyerhenke
2011 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum  
We present a framework based on the STINGER data structure that can monitor a global property, connected components, on a graph of 16 million vertices at rates of up to 240 000 updates per second on 32  ...  The massive state behind multiple persistent queries requires shared data structures and flexible representations.  ...  We thank PNNL and Cray for providing access to Cray XMT systems.  ... 
doi:10.1109/ipdps.2011.326 dblp:conf/ipps/EdigerRBM11 fatcat:bi72vxpjmbdwlmnvncwclyygxa

A near optimal isosurface extraction algorithm using the span space

Y. Livnat, Han-Wei Shen, C.R. Johnson
1996 IEEE Transactions on Visualization and Computer Graphics  
the data set and k is the number of cells intersected by the isosurface.  ...  The memory requirement is kept at O(n) while the preprocessing step is O(n log n).  ...  We wish to thank the Los Alamos National Laboratory for the the use of their facilities and the Head data set. The FD data set is courtesy of Shi-Yi Chen of LANL.  ... 
doi:10.1109/2945.489388 fatcat:c4dqztv6bval3hw2c7nfieoq5i

Wavelet-based Multiresolution Isosurface Rendering [article]

Markus Steinberger, Markus Grabner
2010 International Workshop on Volume Graphics, Proceedings of the  
The underlying trivariate function is represented as a spline wavelet hierarchy, which allows for adaptive (view-dependent) selection of the desired level-of-detail by superimposing appropriately weighted  ...  Both wavelet reconstruction and root finding are implemented in CUDA to utilize the high computational performance of Nvidia's hardware and to obtain high quality results.  ...  This work was partially sponsored by the Austrian Science Fund FWF under contract W1209.  ... 
doi:10.2312/vg/vg10/013-020 fatcat:hlyh6zlxhjaf5ejbljqrx5tmyi

A hybrid representation for modeling, interactive editing, and real-time visualization of terrains with volumetric features

Çetin Koca, Uğur Güdükbay
2014 International Journal of Geographical Information Science  
They can represent volumetric features but they require computationally intensive algorithms for rendering, and their memory requirements are high.  ...  This decreases the amount of data to be processed and the amount of processing power needed, but at the cost of expressivity and the ability to create complex terrains.  ...  Türker Yılmaz for valuable comments and suggestions, Rana Nelson for proofreading and Ateş Akaydın for narrating the videos.  ... 
doi:10.1080/13658816.2014.900560 fatcat:rzjhwhgozjgqrjmtohtxjrbgt4

Massively-parallel vector graphics

Francisco Ganacim, Rodolfo S. Lima, Luiz Henrique de Figueiredo, Diego Nehab
2014 ACM Transactions on Graphics  
It groups together samples that can be computed with the same vector operations using little memory or bandwidth.  ...  Our sample scheduler allows pixels with overlapping antialiasing filters to share samples.  ...  All tests were run on an NVIDIA GeForce GTX Titan (2688 CUDA cores, 6GB of global memory) hosted by an Intel Core i7 980 at 3.33GHz with 24GB of system memory.  ... 
doi:10.1145/2661229.2661274 fatcat:klzccho3vjeevnwd4uv3o7oggq

Interactive Volume Rendering with Ray Tracing [article]

Gerd Marmitt, Heiko Friedrich, Philipp Slusallek
2006 Eurographics State of the Art Reports  
Recent research on high-performance ray tracing has achieved real-time performance even for highly complex surface models already on a single PC.  ...  We present optimized implementations and discuss the use of upcoming high-performance processors for volume ray tracing.  ...  Acknowledgements We would like to thank all the people that contributed to this report, either by comments and suggestions or by making images available: In particular we thank Holger Theisel for discussion  ... 
doi:10.2312/egst.20061055 fatcat:jgqba5cix5bu3oqmqr6rc222zq

GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge [article]

Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, Ravi Netravali
2022 arXiv   pre-print
Our system, GEMEL, efficiently integrates merging into existing pipelines by (1) leveraging several guiding observations about per-model memory usage and inter-layer dependencies to quickly identify fruitful  ...  Unfortunately, existing solutions that rely on time/space sharing of GPU resources are insufficient as the required swapping delays result in unacceptable frame drops and accuracy violations.  ...  memory wins quickly, but also to quickly respond to workload changes.  ... 
arXiv:2201.07705v2 fatcat:aqdf4rdhlrgbjehljg3mfk5auq

FLASH: Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search [article]

Yiqiu Wang, Anshumali Shrivastava, Jonathan Wang, Junghee Ryu
2018 arXiv   pre-print
Current state-of-the-art implementations either fail on the presented scale or are orders of magnitude slower than FLASH.  ...  We present FLASH (Fast LSH Algorithm for Similarity search accelerated with HPC), a similarity search system for ultra-high dimensional datasets on a single machine, that does not require similarity computations  ...  We would like to thank anonymous reviewers and Rasmus Pagh for discussions on the role of correlations in Theorem 1.  ... 
arXiv:1709.01190v2 fatcat:vic3h5gjnbfnppyruoc4io6rsu

Exploiting Local Orientation Similarity for Efficient Ray Traversal of Hair and Fur [article]

Sven Woop, Carsten Benthin, Ingo Wald, Gregory S. Johnson, Eric Tabellion
2014 High Performance Graphics  
This BVH exploits similarity in the orientation of neighboring hairs to increase ray culling efficiency compared to purely axis-aligned BVHs.  ...  Our approach achieves about 2× the performance of ray tracing pre-tessellated hair models, while requiring significantly less memory.  ...  Acknowledgments We would like to thank DreamWorks Animation for providing the models in Figure 1 and 4 and for supporting this work.  ... 
doi:10.2312/hpg.20141092 fatcat:26b5bcvw65aifmstft6k66vfvu

Hadoop GIS

Ablimit Aji, Fusheng Wang, Hoang Vo, Rubao Lee, Qiaoling Liu, Xiaodong Zhang, Joel Saltz
2013 Proceedings of the VLDB Endowment  
In this paper, we present Hadoop-GIS -a scalable and high performance spatial data warehousing system for running large scale spatial queries on Hadoop.  ...  Our experiments have demonstrated the high efficiency of Hadoop-GIS on query response and high scalability to run on commodity clusters.  ...  We count the number of objects in each tile, and sort them based on the counts. We define a threshold Cmax as the maximal count of objects allowed in a tile.  ... 
doi:10.14778/2536222.2536227 fatcat:z7w7hmd23na4flngnhyfvapbe4

Hadoop-GIS: A High Performance Spatial Data Warehousing System over MapReduce

Ablimit Aji, Fusheng Wang, Hoang Vo, Rubao Lee, Qiaoling Liu, Xiaodong Zhang, Joel Saltz
2013 Proceedings of the VLDB Endowment  
In this paper, we present Hadoop-GIS - a scalable and high performance spatial data warehousing system for running large scale spatial queries on Hadoop.  ...  Our experiments have demonstrated the high efficiency of Hadoop-GIS on query response and high scalability to run on commodity clusters.  ...  Acknowledgments This work is supported in part by PHS Grant UL1RR025008 from the CTSA program, R24HL085343 from the NHLBI, by Grant Number R01LM009239 from the NLM, by NCI Contract No.  ... 
pmid:24187650 pmcid:PMC3814183 fatcat:v5ov5f6vhzcklbkoyztq7zovda
« Previous Showing results 1 — 15 out of 3,577 results