Deep Learning Enhancing Performance Using Support Vector Machine HTM Cortical Learning Algorithm

Deep Learning Enhancing Performance Using Support Vector Machine HTM Cortical Learning Algorithm D. Akila Souvik Pal R. Jayakarthik Sitikantha Chattopadhyay Ahmed J. Obaid Abstract Deep Learning is a function of AI that duplicates the mechanisms of human thought in the processing of information and selection processes. The aim of this study is to apply a technology known as SVMHTMC to improve deep learning. The HTM Cortical Learning Approach and the Support Vector Machine have been combined in this suggested algorithm. The deep learning technique is based on the assumption that the mean absolute percentage error is reduced. Aside from the overlapping duty cycle, the high proportion of which shows the speed of the classifier’s processing function. The findings demonstrate that by halving the value, the suggested set of criteria minimizes the absolute proportion of mistakes. In addition, raise the percentage of overlapping duty cycles by 17%. 07 01 2021 012144 http://dx.doi.org/10.1088/crossmark-policy iopscience.iop.org Deep Learning Enhancing Performance Using Support Vector Machine HTM Cortical Learning Algorithm Journal of Physics: Conference Series paper Published under licence by IOP Publishing Ltd http://creativecommons.org/licenses/by/3.0/ https://iopscience.iop.org/info/page/text-and-data-mining 10.1088/1742-6596/1963/1/012144 https://iopscience.iop.org/article/10.1088/1742-6596/1963/1/012144 https://iopscience.iop.org/article/10.1088/1742-6596/1963/1/012144/pdf https://iopscience.iop.org/article/10.1088/1742-6596/1963/1/012144/pdf https://iopscience.iop.org/article/10.1088/1742-6596/1963/1/012144 https://iopscience.iop.org/article/10.1088/1742-6596/1963/1/012144/pdf Knowledge-Based Systems Qi 107 54 2016 10.1016/j.knosys.2016.05.055 When ensemble learning meets deep learning: a new deep support vector machine for classification Neurocomputing Kim 165 111 2015 10.1016/j.neucom.2014.09.086 Deep learning with support vector data description Ju 257 2015 Deep learning using linear support vector machines Tang 2013 Neural Networks Kim 64 19 2015 10.1016/j.neunet.2014.09.007 Deep learning of support vector machines with class probability output networks Agrawal 141 2014 Zhuo 2452 2012 IEEE Transactions on Emerging Topics in Computational Intelligence Zyarah 3 4 2019 10.1109/TETCI.2018.2850314 Neuromorphic architecture for the hierarchical temporal memory Afeefa 1 2017 CoRR, abs/1306.0239 Tang 2 2013 Deep learning using support vector machines Lauzon 1438 2012 Maltoni 2011 Suseendran 10.1109/IœA51614.2021.9442621 1 2021 International Journal on Advanced Science Engineering and Information Technology Tawfiq 7 1178 2017 10.18517/ijaseit.7.4.2803 A Survey on Web Mining Techniques and Applications Journal of Engineering and Applied Science Tawfiq 8 8270 2017 Proposed Method for Web Pages Clustering Using Latent Semantic Analysis