Comprehensive Analysis of the Uses of GPU and CUDA in Soft-Computing Techniques

Now a day it is quite often seen that Soft-computing approaches are the cast off frequently in Computer and Information Technology. Fuzzy logic, Genetic Algorithms, and Artificial Neural Network are the fundamentals of Soft computing techniques. Several soft computing approaches such as deep neural network require a huge amount of computational power of the CPU to execute a problem and consume lots of time to execute. GPU (Graphics Processing Unit) provides an efficient way to use efficiently all the computational resources in the form of streaming processors. Further, CUDA (Computed Unified Device Architecture) provides a parallel framework specifically designed for GPU. CUDA and GPU are frequently used to implement different soft computing techniques. This article provides a brief introduction of GPU and CUDA and different soft computing techniques. Further, analytical review of the implementation of different soft computing techniques using GPU and CUDA are given.

[1]  Michal Pavlech.  Self-organizing Migration Algorithm on GPU with CUDA , 2012, SOCO.

[2]  Yong Dou,et al.  Optimized deep belief networks on CUDA GPUs , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[3]  Davood Toghraie,et al.  Designing an artificial neural network to predict dynamic viscosity of aqueous nanofluid of TiO2 using experimental data , 2016 .

[4]  Abdul Rahim Ahmad,et al.  Measuring GPU-accelerated parallel SVM performance using large datasets for multi-class machine learning problem , 2014, Proceedings of the 6th International Conference on Information Technology and Multimedia.

[5]  Veronica Oliveira de Carvalho,et al.  Combining K-Means and K-Harmonic with Fish School Search Algorithm for data clustering task on graphics processing units , 2016, Appl. Soft Comput..

[6]  Jaume Bacardit,et al.  Large-scale experimental evaluation of GPU strategies for evolutionary machine learning , 2016, Inf. Sci..

[7]  Donald C. Wunsch,et al.  Unsupervised Feature Learning Classification With Radial Basis Function Extreme Learning Machine Using Graphic Processors , 2017, IEEE Transactions on Cybernetics.

[8]  Salvatore Cuomo,et al.  On GPU–CUDA as preprocessing of fuzzy-rough data reduction by means of singular value decomposition , 2018, Soft Comput..

[9]  Hidetoshi Ando,et al.  Improvements of Classification Accuracy of Film Defects by Using GPU-accelerated Image Processing and Machine Learning Frameworks , 2016, 2016 Nicograph International (NicoInt).

[10]  I. G. Persiantsev,et al.  Multifold Acceleration of Neural Network Computations Using GPU , 2009, ICANN.

[11]  Bo Yang,et al.  Accelerating nearest neighbor partitioning neural network classifier based on CUDA , 2018, Eng. Appl. Artif. Intell..

[12]  Francisco Javier Díaz Pernas,et al.  Adaptative Resonance Theory Fuzzy Networks Parallel Computation Using CUDA , 2009, IWANN.

[13]  Noel Lopes,et al.  Towards adaptive learning with improved convergence of deep belief networks on graphics processing units , 2014, Pattern Recognit..

[14]  Dilza Szwarcman,et al.  Speeding Up the Training of Neural Networks with CUDA Technology , 2012, ICAISC.

[15]  Rafael Rieder,et al.  Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review , 2018, Comput. Electron. Agric..

[16]  Jaume Bacardit,et al.  Speeding up the evaluation of evolutionary learning systems using GPGPUs , 2010, GECCO '10.

[17]  Devrim Akgün,et al.  GPU accelerated training of image convolution filter weights using genetic algorithms , 2015, Appl. Soft Comput..

[18]  Lei Guo,et al.  Implementation of Neural Network Backpropagation in CUDA , 2013 .

[19]  E. Cooper,et al.  E. J. Will , 1985 .

[20]  Zeshui Xu,et al.  Soft computing based on maximizing consensus and fuzzy TOPSIS approach to interval-valued intuitionistic fuzzy group decision making , 2015, Appl. Soft Comput..

[21]  Qi Li,et al.  Parallel multitask cross validation for Support Vector Machine using GPU , 2013, J. Parallel Distributed Comput..

[22]  Konstantinos I. Diamantaras,et al.  Parallel pattern classification utilizing GPU-based kernelized Slackmin algorithm , 2017, J. Parallel Distributed Comput..

[23]  Miriam Bellver,et al.  Distributed training strategies for a computer vision deep learning algorithm on a distributed GPU cluster , 2017, ICCS.

[24]  Roberto E. Gonz'alez,et al.  Galaxy detection and identification using deep learning and data augmentation , 2018, Astron. Comput..

[25]  Koji Nakano,et al.  Single Kernel Soft Synchronization Technique for Task Arrays on CUDA-enabled GPUs, with Applications , 2017, 2017 Fifth International Symposium on Computing and Networking (CANDAR).

[26]  Mrs. Sonia Kuwelkar,et al.  Implementation of machine learning algorithm for character recognition on GPU , 2017, 2017 International Conference on Computing Methodologies and Communication (ICCMC).

[27]  Ying Liu,et al.  High Performance Geological Disaster Recognition using Deep Learning , 2018, ITQM.

[28]  Frederico G. Guimarães,et al.  A GPU deep learning metaheuristic based model for time series forecasting , 2017 .

[29]  Yuzo Iano,et al.  GPU Cuda JSEG Segmentation Algorithm associated with Deep Learning Classifier for Electrical Network Images Identification , 2018, KES.