Understanding Convolutional Neural Networks with A Mathematical Model

Abstract

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): 1) why a non-linear activation function is essential at the filter output of every convolutional layer? 2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the "REctified-COrrelations on a Sphere" (RECOS) is proposed to answer these two questions. After the CNN training process, the converged filter weights define a set of anchor vectors in the RECOS model. Anchor vectors represent the frequently occurring patterns (or the spectral components). The necessity of rectification is explained using the RECOS model. Then, the behavior of a two-layer RECOS system is analyzed and compared with its one-layer counterpart. The LeNet-5 and the MNIST dataset are used to illustrate discussion points. Finally, the RECOS model is generalized to a multi-layer system with the AlexNet as an example. Keywords: Convolutional Neural Network (CNN), Nonlinear Activation, RECOS Model, Rectified Linear Unit (ReLU), MNIST Dataset.

References in corpus (11)

• Intriguing properties of neural networks
• Understanding Neural Networks Through Deep Visualization
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Object Detectors Emerge in Deep Scene CNNs
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• On the Expressive Power of Deep Learning: A Tensor Analysis
• Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
• Visualizing and Comparing Convolutional Neural Networks
• A New Method to Visualize Deep Neural Networks
• Evaluating the visualization of what a Deep Neural Network has learned
• Towards Better Analysis of Deep Convolutional Neural Networks