在CIFAR-10上对比全连接与卷积网络，揭示学习与记忆的差异。
Experimental Analysis of Neural Network-Based Image Classification on the CIFAR-10 Dataset
- 采用六层卷积+三阶段池化，批量大小128，学习率0.001训练10轮
- 验证准确率达74.77%，训练损失持续下降但验证损失中途上升
- 提供可复现的基准，适合研究正则化与数据增强方法
本文通过全连接与卷积网络架构，在CIFAR-10基准上开展神经图像分类实验。分析涵盖完整学习流程：图像向量化、归一化、独热编码、监督损失最小化、学习率选择、小批量训练、卷积特征提取、最大池化及基于验证集的泛化评估。采用含六层卷积和三阶段最大池化的架构，以128批次大小、Adam优化器、0.001学习率进行十轮训练。验证准确率达到约74.77%，尽管训练损失持续下降，验证损失在中段后开始上升。该现象揭示了表征学习与记忆之间的实际差异，并为正则化、数据增强、更深架构研究及可复现的图像分类教学提供了紧凑实验基线。
原文摘要 · Abstract (English)
An experimental investigation of neural image classification on the CIFAR-10 benchmark is presented through fully connected and convolutional network formulations. The analysis emphasizes the complete learning pipeline: image vectorization, normalization, one-hot class encoding, supervised loss minimization, learning-rate selection, mini-batch training, convolutional feature extraction, max-pooling, and validation-based generalization assessment. A convolutional architecture with six convolutional layers and three max-pooling stages is evaluated for ten training epochs using a batch size of 128 and an Adam optimizer with a learning rate of 0.001. The validation accuracy reaches approximately 74.77%, while the validation loss begins to increase after the middle of training despite continued reduction in training loss. The resulting behavior illustrates the practical difference between representation learning and memorization, and it provides a compact experimental baseline for future studies on regularization, data augmentation, deeper architectures, and reproducible image-classification education.
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。