Arrange the following steps in the correct order to explain the importance of network depth in neural networks for visual recognition tasks: A) Network depth increases the capacity for feature extraction, B) Deeper networks can integrate complex features more effectively, C) The model achieves higher classification accuracy, D) Training becomes more challenging due to vanishing gradients.

Depth first increases a network’s capacity to extract features, because each additional layer can learn a new representation. With more layers, the model can integrate these representations into increasingly complex features, enabling it to capture subtle visual patterns. However, adding layers makes training harder because gradients can vanish, requiring tricks like residual connections. Despite the training difficulty, the richer feature hierarchy typically yields higher classification accuracy. For instance, a 50‑layer ResNet outperforms a 10‑layer version on ImageNet, illustrating the trade‑off between depth, training challenge, and accuracy.