Filters








2,262 Hits in 5.9 sec

Speeding up the evaluation of evolutionary learning systems using GPGPUs

María A. Franco, Natalio Krasnogor, Jaume Bacardit
2010 Proceedings of the 12th annual conference on Genetic and evolutionary computation - GECCO '10  
In this paper we introduce a method for computing fitness in evolutionary learning systems based on NVIDIA's massive parallel technology using the CUDA library.  ...  This method has been integrated within the BioHEL evolutionary learning system. The methodology presented in this paper can be easily extended to any evolutionary learning system.  ...  GPGPUs have been used already to speed up the evaluation process in genetic algorithms [14] , genetic programming [11] and learning classifier systems (LCS) [13] .  ... 
doi:10.1145/1830483.1830672 dblp:conf/gecco/FrancoKB10 fatcat:umzgywfyfjbvxfgqu4ozinepvq

Implementation of Scale and Rotation Invariant On-Line Object Tracking Based on CUDA

Quan MIAO, Guijin WANG, Xinggang LIN
2011 IEICE transactions on information and systems  
The algorithm is based on NVIDIA's Graphics Processing Units (GPU) using Compute Unified Device Architecture (CUDA), following the model of single instruction multiple threads.  ...  Object tracking is a major technique in image processing and computer vision. Tracking speed will directly determine the quality of applications.  ...  The object region is transformed using the homography estimated based on the matching candidates. In [7] , we further expand the idea and provide in detail a new framework.  ... 
doi:10.1587/transinf.e94.d.2549 fatcat:oioinqminzf7rnk6zo5bprghce

Classifying chemical sensor data using GPU-accelerated bio-mimetic neuronal networks based on the insect olfactory system

Alan Diamond, Michael Schmuker, Amalia Z Berna, Stephen Trowell, Thomas Nowotny
2014 BMC Neuroscience  
Classification accuracy is compared with support vector machine (SVM) learning which we also look to match for speed through the use of GPU accelerated neural simulation [5] via the NVidia CUDA TM -based  ...  We present results of applying an insect-inspired approach to the design of a learning spiking neural network that receives synchronized time series data from up to 12 metal-oxide based gas sensors, comprising  ...  Classification accuracy is compared with support vector machine (SVM) learning which we also look to match for speed through the use of GPU accelerated neural simulation [5] via the NVidia CUDA TM -based  ... 
doi:10.1186/1471-2202-15-s1-p77 pmcid:PMC4126557 fatcat:5dq6vbcxoza4bn4uhslkdgf5ie

Parallel evaluation of Pittsburgh rule-based classifiers on GPUs

Alberto Cano, Amelia Zafra, Sebastián Ventura
2014 Neurocomputing  
In this paper we propose a parallel evaluation model of rules and rule sets on GPUs based on the NVIDIA CUDA programming model which significantly allows reducing the run-time and speeding up the algorithm  ...  The GPU model achieves a rule interpreter performance of up to 64 billion operations per second and the evaluation of the individuals is speeded up of up to 3.461× when compared to the CPU model.  ...  One method based on this approach is the Memetic Pittsburgh Learning Classifier System (MPLCS) [8] .  ... 
doi:10.1016/j.neucom.2013.01.049 fatcat:3mxhr6qrrjhkpmc2hakoo2kcyi

Accelerating Computer-Based Recognition of Fynbos Leaves Using a Graphics Processing Unit

Simon Lucas Winberg, Moeko Ramone, Khagendra Naidoo
2017 South African Computer Journal  
The C++ version was noticeable faster than the original prototype, achieving an average speed-up of 8.7 for high-resolution 3456x2304 pixel images.  ...  Further work on this project involves testing the system with a wider variety of leaves and trying different machine learning algorithms for the leaf prediction routines.  ...  This was done to more closely match normal use. Using the final average execution times for each FLORA implementation, the speed-ups achieved in FLORA-C and FLORA-G could then be determined.  ... 
doi:10.18489/sacj.v29i3.432 fatcat:qjqgjcektjdyrfjrdxzkua6i74

Large scale data mining using genetics-based machine learning

Jaume Bacardit, Xavier Llorà
2009 Proceedings of the 11th annual conference companion on Genetic and evolutionary computation conference - GECCO '09  
large- scale datasets • We recently extended it with a CUDA-based fitness computation (Franco, Krasnogor & Bacardit, 2010) Performance of BioHEL using CUDA • We used CUDA in a Tesla C1060 card  ...  build such a function • Cheap surrogates can help avoid costly evaluations that tend to dominate execution time Hybrid Methods • The Memetic Pittsburgh Learning Classifier Systems (MPLCS) combines  ... 
doi:10.1145/1570256.1570424 dblp:conf/gecco/BacarditL09 fatcat:gnpp6egslzf7fjnyxkt2naqwam

Large scale data mining using genetics-based machine learning

Jaume Bacardit, Xavier Llorà
2011 Proceedings of the 13th annual conference companion on Genetic and evolutionary computation - GECCO '11  
large- scale datasets • We recently extended it with a CUDA-based fitness computation (Franco, Krasnogor & Bacardit, 2010) Performance of BioHEL using CUDA • We used CUDA in a Tesla C1060 card  ...  build such a function • Cheap surrogates can help avoid costly evaluations that tend to dominate execution time Hybrid Methods • The Memetic Pittsburgh Learning Classifier Systems (MPLCS) combines  ... 
doi:10.1145/2001858.2002137 dblp:conf/gecco/BacarditL11 fatcat:bgbkp6youfauxnc7jetrpjwj4q

Large scale data mining using genetics-based machine learning

Jaume Bacardit, Xavier Llorà
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion - GECCO Companion '12  
large- scale datasets • We recently extended it with a CUDA-based fitness computation (Franco, Krasnogor & Bacardit, 2010) Performance of BioHEL using CUDA • We used CUDA in a Tesla C1060 card  ...  build such a function • Cheap surrogates can help avoid costly evaluations that tend to dominate execution time Hybrid Methods • The Memetic Pittsburgh Learning Classifier Systems (MPLCS) combines  ... 
doi:10.1145/2330784.2330936 dblp:conf/gecco/BacarditL12 fatcat:7qpgc572efg5zk3zkz4px3pky4

Large scale data mining using genetics-based machine learning

Jaume Bacardit, Xavier Llorà
2013 Proceeding of the fifteenth annual conference companion on Genetic and evolutionary computation conference companion - GECCO '13 Companion  
large- scale datasets • We recently extended it with a CUDA-based fitness computation (Franco, Krasnogor & Bacardit, 2010) Performance of BioHEL using CUDA • We used CUDA in a Tesla C1060 card  ...  build such a function • Cheap surrogates can help avoid costly evaluations that tend to dominate execution time Hybrid Methods • The Memetic Pittsburgh Learning Classifier Systems (MPLCS) combines  ... 
doi:10.1145/2464576.2480807 dblp:conf/gecco/BacarditL13 fatcat:g7weaaxqsrdytcnalrucleoz4u

Towards a robust, real-time face processing system using CUDA-enabled GPUs

Bharatkumar Sharma, Rahul Thota, Naga Vydyanathan, Amit Kale
2009 2009 International Conference on High Performance Computing (HiPC)  
Face detection is done by adapting the Viola and Jones algorithm that is based on the Adaboost learning system.  ...  We evaluate our face processing system using both static image databases as well as using live frames captured from a firewire camera under realistic conditions.  ...  To speed up this feature computation, Viola and Jones proposed the use of the integral image.  ... 
doi:10.1109/hipc.2009.5433189 dblp:conf/hipc/SharmaTVK09 fatcat:lalinzvrsnf2hgxrw3ievgbkeq

Speeding up the evaluation phase of GP classification algorithms on GPUs

Alberto Cano, Amelia Zafra, Sebastián Ventura
2011 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
This paper proposes an efficient scalable and massively parallel evaluation model using the NVIDIA CUDA GPU programming model to speedup the fitness calculation phase and greatly reduce the computational  ...  The efficiency of evolutionary algorithms has become a studied problem since it is one of the major weaknesses in these algorithms.  ...  Acknowledgements This work has been financed in part by the TIN2008-06681-C06-03 project of the Spanish Inter-Ministerial Commission of Science and Technology (CICYT), the P08-TIC-3720 project of the Andalusian  ... 
doi:10.1007/s00500-011-0713-4 fatcat:urjdgasx4vbwdhlj24qlzockfy

GENETIC ALGORITHM ON GENERAL PURPOSE GRAPHICS PROCESSING UNIT: PARALLELISM REVIEW

Umbarkar A.J., Joshi M.S., Rothe N.M.
2013 ICTACT Journal on Soft Computing  
Paper gives review of various applications solved using GAs on GPGPU with the future scope in the area of optimization.  ...  Thus, speedup can definitely be achieved if bottleneck in GAs are identified and implemented effectively on GPGPU.  ...  To tackle all these problems, mentioned above, one can use the GPGPU and can exploit its functionality to solve GA effectively with more speed up.  ... 
doi:10.21917/ijsc.2013.0074 fatcat:o33o3fo2ujfuvk6d4x2j3ru47a

An efficient common substrings algorithm for on-the-fly behavior-based malware detection and analysis

Jaime C. Acosta, Humberto Mendoza, Brenda G. Medina
2012 MILCOM 2012 - 2012 IEEE Military Communications Conference  
The algorithm is implemented in the CUDA and results show a performance increase of up to 8 times compared to previous implementations.  ...  The algorithm finds common substrings between malware pairs in theoretical linear time by using parallel processing.  ...  [9] use machine learning to identify similarities in malware instances by comparing their dynamic event traces, which include system calls, their dependencies, and network behavior.  ... 
doi:10.1109/milcom.2012.6415819 dblp:conf/milcom/AcostaMM12 fatcat:ngvkboor5rd6xkhfokwq34v3cq

Multicore and GPU Parallelization of Neural Networks for Face Recognition

Altaf Ahmad Huqqani, Erich Schikuta, Sicen Ye, Peng Chen
2013 Procedia Computer Science  
We focus on two specific parallelization environments, using on the one hand OpenMP on a conventional multithreaded CPU and CUDA on a GPU.  ...  In this paper we develop and analyze two novel parallel training approaches for Backpropagation neural networks for face recognition.  ...  (b) Speed up (128x120).  ... 
doi:10.1016/j.procs.2013.05.198 fatcat:lrotpnm5nnf3dhbjzcjfsezflu

GPU-ASIFT: A fast fully affine-invariant feature extraction algorithm

Valeriu Codreanu, Feng Dong, Baoquan Liu, Jos B.T.M. Roerdink, David Williams, Po Yang, Burhan Yasar
2013 2013 International Conference on High Performance Computing & Simulation (HPCS)  
We have created a CUDA version of this algorithm that is up to 70 times faster than the original implementation, while keeping the algorithm's accuracy close to that of ASIFT.  ...  Also, this approach was adapted to fit the multi-GPU paradigm in order to assess the acceleration potential from modern GPU clusters.  ...  Also, we aim at using these highly accurate descriptors as input data to machine learning classifiers and address challenging object recognition datasets like the PascalVOC and Caltech-256 [25] [26  ... 
doi:10.1109/hpcsim.2013.6641456 dblp:conf/ieeehpcs/CodreanuDLRWYY13 fatcat:qwlpnjltzrgnhdptj2vpdftjaa
« Previous Showing results 1 — 15 out of 2,262 results