Deep Neural Networks (DNN) and especially Convolutional Neural Networks (CNN) are a de-facto standard for the analysis of large volumes of signals and images. Yet, their development and underlying principles have been largely performed in an ad-hoc and black box fashion. To help demystify CNNs, we revisit their operation from first principles and a matched filtering perspective. We establish that the convolution operation within CNNs, their very backbone, represents a matched filter which examines the input signal/image for the presence of pre-defined features. This perspective is shown to be physically meaningful, and serves as a basis for a step-by-step tutorial on the operation of CNNs, including pooling, zero padding, various ways of dimensionality reduction. Starting from first principles, both the feed-forward pass and the learning stage (via back-propagation) are illuminated in detail, both through a worked-out numerical example and the corresponding visualizations. It is our hope that this tutorial will help shed new light and physical intuition into the understanding and further development of deep neural networks.
翻译:深神经网络(DNN),特别是进化神经网络(CNN),是分析大量信号和图像的一个实际标准。然而,它们的发展和基本原则在很大程度上是以临时和黑盒方式实施的。为了帮助消除CNN的神秘性,我们从最初的原则和相匹配的过滤角度重新审视其运作。我们确定CNN内部的 Convolution 行动,即其主干线,是一个匹配的过滤器,它检查了输入信号/图像,以显示预设的特征的存在。这个视角在物理上是有意义的,并成为对CNN的运作进行逐步辅导的基础,包括汇集、零垫式、多种维度削减方式。从最初的原则开始,通过一个固定的数字示例和相应的直观化,对进食道和学习阶段(通过反向调整)进行详细介绍。我们希望,这一辅导将有助于将新的光和物理直观带带入深神经网络的理解和进一步发展。