Analyzing the Linear and Nonlinear Transformations of AlexNet to Gain Insight into Its Performance

Abstract

AlexNet, one of the earliest and successful deep learning networks, has given great performance in image classification task. There are some fundamental properties for good classification such as: the network preserves the important information of the input data; the network is able to see differently, points from different classes. In this work we experimentally verify that these core properties are followed by the AlexNet architecture. We analyze the effect of linear and nonlinear transformations on input data across the layers. The convolution filters are modeled as linear transformations. The verified results motivate to draw conclusions on the desirable properties of transformation matrix that aid in better classification.