2025/07/08 by Mustafa Bayram Gücen, Gücen, Mustafa Bayram
Computer Science · Neuroscience · #Activation function #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Artificial neural network #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #Convergence (economics) #Convolutional neural network #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Function (biology) #Generalization #MNIST database #Neural and Evolutionary Computing (cs.NE) #Pattern recognition (psychology)
paper · pdf · doi:10.48550/arxiv.2507.06148
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
In this study, SoftReMish, a new activation function designed to improve the performance of convolutional neural networks (CNNs) in image classification tasks, is proposed. Using the MNIST dataset, a standard CNN architecture consisting of two convolutional layers, max pooling, and fully connected layers was implemented. SoftReMish was evaluated against popular activation functions including ReLU, Tanh, and Mish by replacing the activation function in all trainable layers. The model performance was assessed in terms of minimum training loss and maximum validation accuracy. Results showed that SoftReMish achieved a minimum loss (3.14e-8) and a validation accuracy (99.41%), outperforming all other functions tested. These findings demonstrate that SoftReMish offers better convergence behavior and generalization capability, making it a promising candidate for visual recognition tasks.