This paper presents an overview of developing Convolutional Neural Network using Genetic Algorithm. CNNs have been quite popular for image recognition and classification problems, but developing and training a CNN is a time-consuming and computationally costly and complex process. In this paper we discuss and review various GA based methods used for automatically generating and developing CNN networks and optimizing their networks for various pattern recognition problems and various tasks on image datasets. This paper looks at how using genetic approach for developing a network reduces its computational complexity compared to the traditional methods and increases the efficiency and accuracy of the network while also making the training process easier. We look at the genetic encoding used to generate a network and perform its evolution. A general survey of developing CNNs using GA is presented in order to understand the improvement in performance achieved through the given method. We look at the relative performance of CNNs developed through genetic approach and make a general comparison with the ones produced manually.

Convolutional Neural Network (CNN), Genetic Algorithm (GA), Neural Networks, Pattern Recognition, Image Classification, Structure Learning, Deep Learning

[1] S. Gibb, H. M. La, S. Louis, “A Genetic Algorithm for Convolutional Network Structure Optimization for Concrete Crack Detection,” in IEEE Congress on Evolutionary Computation, pp. 1-8, 2018.
[2] L. Xie, A. Yuille, “Genetic CNN,” in IEEE International Conference on Computer Vision, pp. 1388-1397, 2017.
[3] H Tian, S Pouyanfar, J Chen, S.C. Chen, S. Iyengar, “Automatic Convolutional Neural Network Selection for Image Classification Using Genetic Algorithms,” in IEEE International Conference on IRI, pp. 444-451, 2018.
[4] Mitchell Melanie, “An Introduction to Genetic Algorithms,” The MIT Press, pp. 49-62, 1996.
[5] Le Zhang , P.N. Suganthan, “A survey of randomized algorithms for training neural networks,” Elsevier Information Sciences, Vol. 364, pp. 146-155, 2016.
[6] Jürgen Schmidhuber, “Deep learning in neural networks: An overview,” Elsevier Neural Networks, Vol. 61, pp. 85-117, 2015.
[7] Tong He, Weilin Huang, Yu Qiao, and Jian Yao, “Text-Attentional Convolutional Neural Network for Scene Text Detection”, IEEE Transaction on Image Processing, Vol. 25, Issue 6, pp. 2529-2541, 2016.
[8] Marco Grond, Willie Brink, and Ben Herbst, “Text Detection in Natural Images with Convolutional Neural Networks and Synthetic Training Data,” in PRASA-RobMech International Conference, 2016.
[9] H. Lit, Z. Lin, X. Shen, J. Brandt, G. Huat, “A Convolutional Neural Network Cascade for Face Detection”, in IEEE Conference on CVPR, pp. 5325-5334, 2015.
[10] H. Liu, X. Shen, H. Ren, “FDAR-Net: Joint Convolutional Neural Networks for Face Detection and Attribute Recognition”, in 9th International SCID, pp 184-187, 2016.
[11] C. Zhang, Z. Zhang, “Improving Multiview Face Detection with Multi-Task Deep Convolutional Neural Networks”, in IEEE WCACV, pp. 1036-1041, 2014.
[12] Kaipeng Zhang, Zhanpeng Zhang, Zhifeng Li, and Yu Qiao, “Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks”, IEEE Signal Processing Letters, pp. 1499-1503, 2016.
[13] C. Nebauer, “Evaluation of convolutional neural networks for visual recognition”, IEEE transactions on Neural Networks,Vol. 9, Issue 4, pp. 685-96, 1998.
[14] J. Schmidhuber, “Deep learning in neural networks: An overview”, Elsevier Neural Networks, Vol. 61, pp. 85-117, 2015.
[15] W. Liu, Z. Wanga, X. Liu, N. Zeng, Y. Liu,, F. E. Alsaadi, “A survey of deep neural network architectures and their applications”, Neurocomputing, Vol. 234, pp. 11-26.
[16] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition”, Proceedings of the IEEE, Vol. 86, no. 11, pp. 2278-2324, 1998.
[17] Christophe Garcia, Manolis Delakis, “Convolutional Face Finder: A Neural Architecture for Fast and Robust Face Detection”, IEEE Trans. on PAMI, Vol. 26, pp. 1408-1423.
[18] Zhan Wu, Min Pengl, Tong Chen, “Thermal Face Recognition Using Convolutional Neural Network”, in International Conference on OIP, pp. 6-9, 2016.
[19] Eli (Omid) David, Iddo Greental, “Genetic Algorithms for Evolving Deep Neural Networks”, GECCO, 2014.
[20] S.R. Young, D.C. Rose, T.P. Karnowski, S.H. Lim, R.M. Patton, “Optimizing Deep Learning Hyper-Parameters Through an Evolutionary Algorithm”, in MLHPC, 2015.
[21] F. Leung, H.K. Lam, S.H. Ling, K.S. Tam, “Tuning of the Structure and Parameters of a Neural Network Using an Improved Genetic Algorithm”, IEEE Trans. on Neural Networks, Vol. 14, No. 1, pp 79-88, 2003.
[22] J.T. Tsai, J.H. Chou,T.K. Liu, “Tuning the Structure and Parameters of a Neural Network by Using Hybrid Taguchi-Genetic Algorithm”. IEEE Transactions on Neural Networks, 17, 69-80, 2006.
[23] D. Hossain, G. Capi, M. Jindai, “Optimizing Deep Learning Parameters Using Genetic Algorithm for Object Recognition and Robot Grasping”, Journal of Electronic Science and Technology, Vol. 16, pp. 11-15, 2018.
[24] Nacéra Benamrane and Abdelkader Fekir, “Medical Images Segmentation By Neuro-Genetic Approach” in Ninth International Conference on Information Visualisation, pp. 981-986, 2005.
[25] Ms. K. Umamaheswari, Dr.S. Sumathi, Dr. S.N. Sivanandam, “Neuro–Genetic approaches to classification of Face Images with effective feature selection using hybrid classifiers”, in International Conference on Advanced Computing and Communications, pp. 286-291, 2006.
[26] T.A. Tarique, M.A. Zamee, M.I. Khan, “A New Approach for Pattern Recognition with Neuro-Genetic System Using Microbial Genetic Algorithm”, in International Conference on EE&ICT, pp. 1-4, 2015.
[27] Y.-J. Cha, W. Choi, O. Bykztrk, “Deep learning-based crack damage detection using convolutional neural networks”, Comp.-Aided Civil and Infrastruct. Engineering, Vol. 32, pp. 361-378, 2017.