|
JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/16196
|
Title: | Mean Spectral Normalization of Deep Neural Networks for Embedded Automation |
Authors: | Subramanian, Anand Krishnamoorthy Chong, Nak Young |
Issue Date: | 2019-08 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Magazine name: | 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE) |
Start page: | 249 |
End page: | 256 |
DOI: | 10.1109/COASE.2019.8842955 |
Abstract: | Deep Neural Networks (DNNs) have begun to thrive in the field of automation systems, owing to the recent advancements in standardising various aspects such as architecture, optimization techniques, and regularization. In this paper, we take a step towards a better understanding of Spectral Normalization (SN) and its potential for standardizing regularization of a wider range of Deep Learning models, following an empirical approach. We conduct several experiments to study their training dynamics, in comparison with the ubiquitous Batch Normalization (BN) and show that SN increases the gradient sparsity and controls the gradient variance. Furthermore, we show that SN suffers from a phenomenon, we call the mean-drift effect, which mitigates its performance. We, then, propose a weight reparameterization called as the Mean Spectral Normalization (MSN) to resolve the mean drift, thereby significantly improving the network's performance. Our model performs ~ 16% faster as compared to BN in practice, and has fewer trainable parameters. We also show the performance of our MSN for small, medium, and large CNNs - 3-layer CNN, VGG7 and DenseNet-BC, respectively and unsupervised image generation tasks using Generative Adversarial Networks (GANs) to evaluate its applicability for a broad range of embedded automation tasks. |
Rights: | This is the author's version of the work. Copyright (C) 2019 IEEE. 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), 2019, 249-256. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
URI: | http://hdl.handle.net/10119/16196 |
Material Type: | author |
Appears in Collections: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
Files in This Item:
File |
Description |
Size | Format |
3052.pdf | | 2870Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|