新激活函数SoftReMish提升图像分类性能，精度达99.41%
SoftReMish: A Novel Activation Function for Enhanced Convolutional Neural Networks for Visual Recognition Performance
- 提出新型激活函数SoftReMish，替代传统ReLU等
- 在MNIST上实现3.14e-8最低损失与99.41%最高准确率
- 适合追求高精度的视觉识别任务研究者使用
本文提出一种新型激活函数SoftReMish，旨在提升卷积神经网络（CNN）在图像分类任务中的表现。基于标准CNN架构（含两层卷积、最大池化和全连接层），在MNIST数据集上进行实验，将SoftReMish与ReLU、Tanh、Mish等常见激活函数对比，替换所有可训练层的激活函数。评估指标为最小训练损失与最大验证准确率。结果表明，SoftReMish达到3.14e-8的最小损失和99.41%的验证准确率，优于所有对比函数。该结果说明SoftReMish具有更优的收敛性与泛化能力，是视觉识别任务的有力候选方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。