Why do CNNs excel at feature extraction? A mathematical explanation
This provides a foundational mathematical explanation for CNNs' effectiveness in feature extraction, addressing a key theoretical gap in deep learning.
The paper tackles the theoretical question of why convolutional neural networks (CNNs) excel at feature extraction for image classification, showing that CNNs can solve image classification tasks with zero error in a novel mathematical model.
Over the past decade deep learning has revolutionized the field of computer vision, with convolutional neural network models proving to be very effective for image classification benchmarks. However, a fundamental theoretical questions remain answered: why can they solve discrete image classification tasks that involve feature extraction? We address this question in this paper by introducing a novel mathematical model for image classification, based on feature extraction, that can be used to generate images resembling real-world datasets. We show that convolutional neural network classifiers can solve these image classification tasks with zero error. In our proof, we construct piecewise linear functions that detect the presence of features, and show that they can be realized by a convolutional network.