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

### Jyoti Nigam, Srishti Barahpuriya, Renu Rameshan

#### 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.

Download#### Paper Citation

#### in Harvard Style

Nigam J., Barahpuriya S. and Rameshan R. (2019). **Analyzing the Linear and Nonlinear Transformations of AlexNet to Gain Insight into Its Performance**.In *Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,* ISBN 978-989-758-351-3, pages 860-865. DOI: 10.5220/0007582408600865

#### in Bibtex Style

@conference{icpram19,

author={Jyoti Nigam and Srishti Barahpuriya and Renu Rameshan},

title={Analyzing the Linear and Nonlinear Transformations of AlexNet to Gain Insight into Its Performance},

booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},

year={2019},

pages={860-865},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0007582408600865},

isbn={978-989-758-351-3},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,

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

SN - 978-989-758-351-3

AU - Nigam J.

AU - Barahpuriya S.

AU - Rameshan R.

PY - 2019

SP - 860

EP - 865

DO - 10.5220/0007582408600865