Applying Improved Convolutional Neural Network in Image Classification

In order to solve the poor accuracy problem which caused by the gradient descent easily fail into local optimum during the training process and the noise interference in process of feature extracting. This paper presents an integrated optimization method of simulated annealing (SA) and Gaussian convolution based on Convolutional Neural Network (CNN). Firstly, the improved algorithm extract some features from the central feature of a model as priori information, and find the optimal solution as initial weights of full-connection layer by simulating annealing, so as to accelerate the weight updating and convergence rate. Secondly, using the Gaussian convolution method, this paper can smooth image to reduce noise disturbing. Finally, the improved integrated optimization method is applied to the MNIST and CIFAR-10 databases. Simulation results show that the accuracy rate of the integrated network is improved through the contrastive analysis of different algorithms.

[1]  Minho Lee,et al.  Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection , 2017, Neural Networks.

[2]  Jacob Chakareski.  Bridging Social and Data Networks [Applications Corner] , 2012, IEEE Signal Process. Mag..

[3]  Yiping Yang,et al.  Rotated region based CNN for ship detection , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[4]  Mohamad Ivan Fanany,et al.  Metaheuristic Algorithms for Convolution Neural Network , 2016, Comput. Intell. Neurosci..

[5]  Guoyin Wang,et al.  Pixel convolutional neural network for multi-focus image fusion , 2017, Inf. Sci..

[6]  Tie Qiu,et al.  EABS: An Event-Aware Backpressure Scheduling Scheme for Emergency Internet of Things , 2018, IEEE Transactions on Mobile Computing.

[7]  Qi Tian,et al.  SIFT Meets CNN: A Decade Survey of Instance Retrieval , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

[9]  Yoshua Bengio,et al.  Equilibrated adaptive learning rates for non-convex optimization , 2015, NIPS.

[10]  Vina Ayumi,et al.  Optimization of convolutional neural network using microcanonical annealing algorithm , 2016, 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS).

[11]  Wenjun Sun,et al.  Induction Motor Fault Diagnosis Based on Deep Neural Network of Sparse Auto-encoder , 2016 .

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Keqiu Li,et al.  How Can Heterogeneous Internet of Things Build Our Future: A Survey , 2018, IEEE Communications Surveys & Tutorials.

[14]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Mehryar Mohri,et al.  Algorithms for Learning Kernels Based on Centered Alignment , 2012, J. Mach. Learn. Res..