SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance
This is an incremental improvement for researchers and practitioners in computer vision, focusing on enhancing activation functions for visual recognition tasks.
The authors tackled improving CNN performance for image classification by proposing a new activation function called SoftReMish, which achieved a validation accuracy of 99.41% and a minimum loss of 3.14e-8 on the MNIST dataset, outperforming ReLU, Tanh, and Mish.
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.