Abstract
This study proposes a modified convolutional neural network (CNN) algorithm that is based on dropout and the stochastic gradient descent (SGD) optimizer (MCNN-DS), after analyzing the problems of CNNs in extracting the convolution features, to improve the feature recognition rate and reduce the time-cost of CNNs. The MCNN-DS has a quadratic CNN structure and adopts the rectified linear unit as the activation function to avoid the gradient problem and accelerate convergence. To address the overfitting problem, the algorithm uses an SGD optimizer, which is implemented by inserting a dropout layer into the all-connected and output layers, to minimize cross entropy. This study used the datasets MNIST, HCL2000, and EnglishHand as the benchmark data, analyzed the performance of the SGD optimizer under different learning parameters, and found that the proposed algorithm exhibited good recognition performance when the learning rate was set to [0.05, 0.07]. The performances of WCNN, MLP-CNN, SVM-ELM, and MCNN-DS were compared. Statistical results showed the following: (1) For the benchmark MNIST, the MCNN-DS exhibited a high recognition rate of 99.97%, and the time-cost of the proposed algorithm was merely 21.95% of MLP-CNN, and 10.02% of SVM-ELM; (2) Compared with SVM-ELM, the average improvement in the recognition rate of MCNN-DS was 2.35% for the benchmark HCL2000, and the time-cost of MCNN-DS was only 15.41%; (3) For the EnglishHand test set, the lowest recognition rate of the algorithm was 84.93%, the highest recognition rate was 95.29%, and the average recognition rate was 89.77%.
Highlights
The convolutional neural network (CNN) has attracted considerable attention because of its successful application in target detection, image classification, knowledge acquisition, and image semantic segmentation
Modified Convolutional Neural Network Based on Dropout and the stochastic gradient descent (SGD) Optimizer
On the basis of the design of the CNN structure, the Leaky ReLU activation function, and the overfitting prevention method that is based on dropout and the SGD, the Modified Convolutional
Summary
The convolutional neural network (CNN) has attracted considerable attention because of its successful application in target detection, image classification, knowledge acquisition, and image semantic segmentation. In [12], two consecutive convolution operations were appended to each layer of the CNN, thereby increasing the recognition rate of image classification by doubling the number of feature extracts. This procedure has high memory requirements from the system. InWhen the regularization the error objective function the considers theoffactors the the number of strategy, learning layers in the CNN increases, capability these that describe the complexity. The time lock decreases, the cumulative error increases To address address these these problems, problems, this this study study designs designs an an improved improved activation activation function function to to increase increase the the convergence rate by adding a dropout layer between the fully connected and output layers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.