RunPool: A Dynamic Pooling Layer for Convolution Neural Network

Abstract

A B S T R A C TDeep learning (DL) has achieved a significant performance in computer vision problems, mainly in automatic feature extraction and representation. However, it is not easy to determine the best pooling method in a different case study. For instance, experts can implement the best types of pooling in image processing cases, which might not be optimal for various tasks. Thus, it is required to keep in line with the philosophy of DL. In dynamic neural network architecture, it is not practically possible to find a proper pooling technique for the layers. It is the primary reason why various pooling cannot be applied in the dynamic and multidimensional dataset. To deal with the limitations, it needs to construct an optimal pooling method as a better option than max pooling and average pooling. Therefore, we introduce a dynamic pooling layer called RunPool to train the convolutional neural network (CNN) architecture. RunPool pooling is proposed to regularize the neural network that replaces the deterministic pooling functions. In the final section, we test the proposed pooling layer to address classification problems with online social network (OSN) dataset.

Combining CNN and Grad-Cam for COVID-19 Disease Prediction and Visual Explanation

“…The main problem with this type of layer is the destruction of some information that could be important to the input features. There are many types of pooling operations, such as average, max, and general, but maxpooling is the main type used for image processing [44]. An example of this is illustrated in Fig.…”

Block-Wise Neural Network for Brain Tumor Identification in Magnetic Resonance Images

“…This layer handles the parameters and is responsible for overfitting. Various pooling layers perform different functions (e.g., max, min, and average); the most frequently used layer is max pooling [33]. The size and output of the pooling layer are calculated using Eqs.…”

Implementation of CNN for Plant Leaf Classification

“…A study discusses building a Javanese script classification dataset to help users detect Javanese characters. The result of this training is that the application of Javanese script classification can produce specific Javanese script pattern recognition rates in real applications [3].…”

“…Other classification models also have been proposed to deal with several classification issues. Current techniques explore numerous works that collaborate with conventional techniques with a temporal model to establish a classification model [3][15] [16].…”