Experimental Analysis of Neural Network-Based Image Classification on the CIFAR-10 Dataset

A new study on arXiv presents an experimental analysis of neural network-based image classification on the CIFAR-10 dataset, comparing fully connected and convolutional architectures. The convolutional network achieved 74.77% validation accuracy after ten epochs, but validation loss increased mid-training, highlighting the difference between representation learning and memorization.

arXiv:2606.18565v1 Announce Type: new Abstract: 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.