{"title":"Bayesian Deep Learning Algorithms for Classifying COVID-19 Images","authors":"I. Oloyede","volume":170,"journal":"International Journal of Computer and Information Engineering","pagesStart":145,"pagesEnd":150,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10011862","abstract":"The study investigates the accuracy and loss of deep learning algorithms with the set of coronavirus (COVID-19) images dataset by comparing Bayesian convolutional neural network and traditional convolutional neural network in low dimensional dataset. 50 sets of X-ray images out of which 25 were COVID-19 and the remaining 20 were normal, twenty images were set as training while five were set as validation that were used to ascertained the accuracy of the model. The study found out that Bayesian convolution neural network outperformed conventional neural network at low dimensional dataset that could have exhibited under fitting. The study therefore recommended Bayesian Convolutional neural network (BCNN) for android apps in computer vision for image detection.","references":"[1]\tA. Mart\u00edn, A. Ashish, B. Paul, B. Eugene, C. Chifeng, C. Craig, S.C. Greg, D. Andy, D. Jeffrey, D. Matthieu, G. Sanjay, G. Lan, H. Andrew, L. Geoffrey, L. Michael, J. Rafal, J. Yangqing, K. Lukasz, K. Manjunath, L. Josh, M. Dan, S. Mike, M. Rajat, M. Sherry, M. Derek, O. Chris, S. Jonathon, S. Benoit, S. Ilya, T. Kunal, T. Paul, V. Vincent, V. Vijay, V. Fernanda, V. Oriol, W. Pete, W. Martin, Y. Yuan, and Z. Xiaoqiang, \u2018TensorFlow: Large-scale machine learning on heterogeneous systems\u2019. Software available from tensorflow.org, 2015.\r\n[2]\tG. Yarin, I. Riashat and G. Zoubin, \u2018Deep Bayesian Active Learning with Image Data\u2019, Workshop on Bayesian Deep Learning, Neural Information Processing Systems, Barcelona, Spain, 2016.\r\n[3]\tJ. Schmidhuber, \u2018Deep learning in neural networks: \u201cAn overview\u2019, Neural Networks, Vol 61, pp 85-117, 2015.\r\n[4]\tY. Li. and Y. Liang, \u2018Learning over parameterized neural networks via stochastic gradient descent on structured data,\u2019 inadvances in Neural Information Processing Systems (NeurIPS), 2018.\r\n[5]\tA. Kendall and Y. Gal, \u2018What uncertainties Do We need in Bayesian deep learning for computer vision?,\u2019 in Advances in Neural Information Processing Systems (NIPS), 2017.\r\n[6]\tH. Jonathan and K. Nal, \u2018Bayesian Inference for Large Scale Image Classification\u2019, arXiv:1908.03491v1 (cs.LG), 2019. \r\n[7]\tD. Giacomo, B. Christopher and Z. Xian, \u2018Bayesian Neural Networks for Cellular Image Classification and Uncertainty Analysis\u2019, bioRxiv preprint doi: https:\/\/doi.org\/10.1101\/824862, 2020.\r\n[8]\tT. Toan, P. Trung, C. Gustavo, P. Lyle and R. Lan, \u2018A Bayesian Data Augmentation Approach for Learning Deep Models\u2019, 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA, 2017.\r\n[9]\tF.K. Chen, R. D. Viljoen, and D.M. Bukowska,\u2018Classification of image artefacts in optical coherence tomography angiography of the choroid in macular diseases\u2019. Clinical & Experimental Ophthalmology, 44(5), 388\u2013399. doi:10.1111\/ceo.12683 2015.\r\n[10]\tM. Krasser, \u2018Variational inference in Bayesian neural networks\u2019. http:\/\/krasserm.github.io\/2019\/03\/14\/bayesian-neural-networks\/ unpublished, 2019.\r\n[11]\tM. Takashi, \u2018Bayesian deep learning: A model-based interpretable approach nonlinear Theory and Its Applications\u2019,\t IEICE, vol. 11, no. 1, pp. 16\u201335 c_ IEICE 2020 DOI: 10.1587\/nolta.11.16\r\n[12]\tR. G. Van and F. L. Drake Jr. Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam. 1995\r\n[13]\tAnaconda Software Distribution. Anaconda Documentation. Anaconda Inc. Retrieved from https:\/\/docs.anaconda.com\/2020.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 170, 2021"}