Classification with Extreme Learning Machine on GPU

The general classification is a machine learning task that tries to assign the best class to a given unknown input vector based on past observations (training data). Most of developed algorithms are very time consuming for large datasets (Support Vector Machine, Deep Neural Networks, etc.). Extreme Learning Machine (ELM) is a high quality classification algorithm that gains much popularity in recent years. This paper shows that the speed of learning of this algorithm may be improved by using GPU platform. Experimental results showed that proposed approach is much faster and provides the same accuracy as the original ELM algorithm. The proposed approach runs completely on GPU platform and thus it may be effectively incorporated within other applications.

[1]  Prabhat,et al.  Artificial Neural Network , 2018, Encyclopedia of GIS.

[2]  P. Baldi,et al.  Searching for exotic particles in high-energy physics with deep learning , 2014, Nature Communications.

[3]  Martin T. Hagan,et al.  Neural network design , 1995 .

[4]  Amaury Lendasse,et al.  Fast Face Recognition Via Sparse Coding and Extreme Learning Machine , 2013, Cognitive Computation.

[5]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[6]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[7]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[8]  Sebastián Ventura,et al.  A Parallel Genetic Programming Algorithm for Classification , 2011, HAIS.

[9]  Václav Snásel,et al.  A PSO-based document classification algorithm accelerated by the CUDA Platform , 2012, 2012 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[10]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[11]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[12]  Hai Jin,et al.  Effective naive Bayes nearest neighbor based image classification on GPU , 2013, The Journal of Supercomputing.

[13]  Fuzhen Zhuang,et al.  Parallel extreme learning machine for regression based on MapReduce , 2013, Neurocomputing.

[14]  Viktor K. Prasanna,et al.  High-Performance Traffic Classification on GPU , 2014, 2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing.

[15]  Sebastián Ventura,et al.  Speeding up the evaluation phase of GP classification algorithms on GPUs , 2012, Soft Comput..

[16]  Majid Ahmadi,et al.  An efficient illumination invariant face recognition framework via illumination enhancement and DD-DTCWT filtering , 2013, Pattern Recognit..

[17]  Alastair Nottingham,et al.  Towards a GPU accelerated virtual machine for massively parallel packet classification and filtering , 2013, SAICSIT '13.

[18]  Tianyou Chai,et al.  Burning state recognition of rotary kiln using ELMs with heterogeneous features , 2013, Neurocomputing.

[19]  Hongming Zhou,et al.  Extreme Learning Machines [Trends & Controversies] , 2013 .

[20]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[21]  John R. Williams,et al.  Parallel multiclass classification using SVMs on GPUs , 2010, GPGPU-3.

[22]  Mahdi Nabiyouni,et al.  A Highly Parallel Multi-class Pattern Classification on GPU , 2012, 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012).

[23]  Fuzhen Zhuang,et al.  A parallel incremental extreme SVM classifier , 2011, Neurocomputing.

[24]  Erkki Oja,et al.  GPU-accelerated and parallelized ELM ensembles for large-scale regression , 2011, Neurocomputing.

[25]  Cheng Wu,et al.  Semi-Supervised and Unsupervised Extreme Learning Machines , 2014, IEEE Transactions on Cybernetics.

[26]  Zhu-Hong You,et al.  Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis , 2013, BMC Bioinformatics.

[27]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[28]  Dipankar Das,et al.  Enhanced SenticNet with Affective Labels for Concept-Based Opinion Mining , 2013, IEEE Intelligent Systems.