Abstract
In the traditional CNN design, the hyperparameters, such as the size of the convolutional kernel and stride, are difficult to determine. In this paper, a new convolutional network architecture, named multi-branch fuzzy architecture network (MBFAN), was proposed for this problem. In MBFAN, some branches with a certain convolutional neural network architecture are connected in parallel. In each branch, a different-sized convolutional kernel is applied. By data training and normalization, a weight is given to each branch. By these weights, the important features in the final output are strengthened. By normalization, the branches were interconnected together, making the training process more efficient. Due to overfitting, with the increase of branches, the MBFAN accuracy increases, and then decreases. The number of branches is optimized when the MBFAN accuracy is highest. On the other hand, the location of the convolutional kernel center in an image has a great influence on the convolutional results. This is also discussed in MBFAN. For the experiments, the proposed MBFAN was adopted and tested in a simple convolutional network and a VGG16 network.
Highlights
With the development of computer technology, the amount of image data has increased rapidly
Some scholars have designed the up-sampling method based on the characteristics of the pooling layer, which was used to explain convolutional neural network (CNN) [17], such as a generative adversarial network (GAN) [18], and so on [8], [19]
In the output of multi-branch fuzzy architecture network (MBFAN), these well-performing branches take a larger proportion by the fuzzy architecture designed in our proposed model
Summary
With the development of computer technology, the amount of image data has increased rapidly. Some scholars have designed the up-sampling method based on the characteristics of the pooling layer, which was used to explain CNN [17], such as a generative adversarial network (GAN) [18], and so on [8], [19]. The hyperparameters, layer architectures, filter size, strides, etc., are difficult to be determined before the result is given out. By selecting different padding sizes and strides, the convolution results can be very different For these reasons, the MBFAN was proposed for traditional convolution neural networks in this paper. In the output of MBFAN, these well-performing branches take a larger proportion by the fuzzy architecture designed in our proposed model.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have