Article
Advancements in Image Classification: A Deep Convolutional Neural Network Approach
Based on the analysis of the error backpropagation algorithm, we propose an innovative training criterion for deep neural networks to achieve maximum interval minimum classification error. This criterion enhances the training process by optimizing the classification performance. In addition, we analyze and combine the cross-entropy loss function with the Modified Multi-Class Cross-Entropy (M3CE) loss function to achieve better classification results. The proposed M3CE-CEc model was tested on two deep learning standard databases, MNIST and CIFAR-10. Experimental results demonstrate that M3CE significantly improves the cross-entropy loss function, serving as an effective supplement to traditional cross-entropy. Our approach, M3CE-CEc, yielded strong performance on both datasets, showing its efficacy in improving image classification tasks.
Full Text Attachment
