Deep architectures consist of tens or hundreds of convolutional layers (CLs) that terminate with a few fully connected (FC) layers and an output layer representing the possible labels of a complex classification task. According to the existing deep learning (DL) rationale, the first CL reveals localized features from the raw data, whereas the subsequent layers progressively extract higher-level features required for refined classification. This article presents an efficient three-phase procedure for quantifying the mechanism underlying successful DL. First, a deep architecture is trained to maximize the success rate (SR). Next, the weights of the first several CLs are fixed and only the concatenated new FC layer connected to the output is trained, resulting in SRs that progress with the layers. Finally, the trained FC weights are silenced, except for those emerging from a single filter, enabling the quantification of the functionality of this filter using a correlation matrix between input labels and averaged output fields, hence a well-defined set of quantifiable features is obtained. Each filter essentially selects a single output label independent of the input label, which seems to prevent high SRs; however, it counterintuitively identifies a small subset of possible output labels. This feature is an essential part of the underlying DL mechanism and is progressively sharpened with layers, resulting in enhanced signal-to-noise ratios and SRs. Quantitatively, this mechanism is exemplified by the VGG-16, VGG-6, and AVGG-16. The proposed mechanism underlying DL provides an accurate tool for identifying each filter's quality and is expected to direct additional procedures to improve the SR, computational complexity, and latency of DL.

翻译：深度架构由数十或数百个卷积层（CL）组成，末端连接少数全连接层（FC）以及一个代表复杂分类任务可能标签的输出层。根据现有深度学习（DL）理论，第一层卷积层从原始数据中提取局部特征，而后续层逐步提取更高层次的特征，用于精细分类。本文提出了一种高效的三阶段程序，用于量化深度学习成功背后的机制。首先，训练深度架构以最大化成功率（SR）。其次，固定前几个卷积层的权重，仅训练与输出层相连的新全连接层，从而得到随层数递增的成功率。最后，抑制训练后的全连接权重，仅保留从单一滤波器产生的连接，通过输入标签与平均输出场之间的相关矩阵量化该滤波器的功能，从而获得一组明确定义的可量化特征。每个滤波器本质上独立于输入标签选择单个输出标签，这似乎会阻碍高成功率的实现；然而，反直觉的是，它识别出潜在输出标签的一个小子集。这一特征是深度学习底层机制的必要组成部分，并随层数逐步强化，从而提升信噪比和成功率。定量上，该机制通过VGG-16、VGG-6和AVGG-16进行实例验证。所提出的深度学习底层机制为识别每个滤波器的质量提供了精确工具，并有望引导额外流程以提升深度学习的成功率、计算复杂度和延迟。