%0 Generic %1 budiman2016distributed %A Budiman, Arif %A Fanany, Mohamad Ivan %A Basaruddin, Chan %D 2016 %K myown %T Distributed Averaging CNN-ELM for Big Data %U http://arxiv.org/abs/1610.02373 %X Increasing the scalability of machine learning to handle big volume of data is a challenging task. The scale up approach has some limitations. In this paper, we proposed a scale out approach for CNN-ELM based on MapReduce on classifier level. Map process is the CNN-ELM training for certain partition of data. It involves many CNN-ELM models that can be trained asynchronously. Reduce process is the averaging of all CNN-ELM weights as final training result. This approach can save a lot of training time than single CNN-ELM models trained alone. This approach also increased the scalability of machine learning by combining scale out and scale up approaches. We verified our method in extended MNIST data set and not-MNIST data set experiment. However, it has some drawbacks by additional iteration learning parameters that need to be carefully taken and training data distribution that need to be carefully selected. Further researches to use more complex image data set are required.

@misc{budiman2016distributed, abstract = {Increasing the scalability of machine learning to handle big volume of data is a challenging task. The scale up approach has some limitations. In this paper, we proposed a scale out approach for CNN-ELM based on MapReduce on classifier level. Map process is the CNN-ELM training for certain partition of data. It involves many CNN-ELM models that can be trained asynchronously. Reduce process is the averaging of all CNN-ELM weights as final training result. This approach can save a lot of training time than single CNN-ELM models trained alone. This approach also increased the scalability of machine learning by combining scale out and scale up approaches. We verified our method in extended MNIST data set and not-MNIST data set experiment. However, it has some drawbacks by additional iteration learning parameters that need to be carefully taken and training data distribution that need to be carefully selected. Further researches to use more complex image data set are required.}, added-at = {2016-10-29T11:15:20.000+0200}, author = {Budiman, Arif and Fanany, Mohamad Ivan and Basaruddin, Chan}, biburl = {https://www.bibsonomy.org/bibtex/27c7364290df7ffdafbfab7990dc2fea6/fanany}, description = {Distributed Averaging CNN-ELM for Big Data}, interhash = {d186ae4b6afe38630e6276be8cd3cc63}, intrahash = {7c7364290df7ffdafbfab7990dc2fea6}, keywords = {myown}, note = {cite arxiv:1610.02373Comment: Submitted to IEEE Transactions on Systems, Man and Cybernetics: Systems}, timestamp = {2016-10-29T11:15:20.000+0200}, title = {Distributed Averaging CNN-ELM for Big Data}, url = {http://arxiv.org/abs/1610.02373}, year = 2016 }