Propagation of Quantification Error Over Convolutional Neural Network layers: PhD Forum
Pages 226 - 227
Abstract
Deep Neural Networks (DNNs) have become a real standard in computer vision as they achieved state-of-the art results in detection, classification and scene understanding. However, training and accelerating large-scale deep neural networks is often constrained by the available computational resources. Using fixed point arithmetic could lighten this at the price of quantification error. This work shows how this error variate at different stages along a neural network for various fixed point representation schemes.
References
[1]
J. T. Huang, J. Li, and D. Yu. Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers. May 2013.
[2]
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. Imagenet classification with deep convolutional neural networks. 2012.
[3]
Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR, abs/1409.1556, 2014.
[4]
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998.
[5]
Hong-Phuc Trinh & Marc Duranton & Michel Paindavoine. Efficient data encoding for convolutional neural network application. ACM (TACO), 2015.
[6]
Anwar. S & Kyuyeon Hwang & Wonyong Sung. Fixed point optimization of deep convolutional neural networks for object recognition. ICASSP, 2015 IEEE International Conference, 2015.
[7]
C. Farabet, C. Poulet, J. Y. Han, and Y. LeCun. Cnp: An fpga-based processor for convolutional networks. In FPL International Conference on, 2009.
[8]
Vinayak Gokhale, Jonghoon Jin, Aysegul Dundar, Berin Martini, and Eugenio Culurciello. A 240 g-ops/s mobile coprocessor for deep neural networks. In The IEEE (CVPR) Workshops, June 2014.
[9]
C. Farabet, B. Martini, B. Corda, P. Akselrod, E. Culurciello, and Y. LeCun. Neuflow: A runtime reconfigurable dataflow processor for vision. In CVPRW'11,IEEE Computer Society Conference.
[10]
Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, and Long. Caffe: Convolutional architecture for fast feature embedding. arXiv, 2014.
[11]
Suyog Gupta, Ankur Agrawal, and Pritish Narayanan. Deep learning with limited numerical precision. JMLR Workshop and Conference Proceedings, 2015.
- Propagation of Quantification Error Over Convolutional Neural Network layers: PhD Forum
Recommendations
Scene text recognition using residual convolutional recurrent neural network
Text is a significant tool for human communication, and text recognition in scene images becomes more and more important. In this paper, we propose a residual convolutional recurrent neural network for solving the task of scene text recognition. The ...
Logarithmic Learning Differential Convolutional Neural Network
AbstractConvolutional Neural Networks (CNNs) have revolutionized image classification through their innovative design and training methodologies in computer vision. Differential convolutional neural network with simultaneous multidimensional filter ...
Differential convolutional neural network
AbstractConvolutional neural networks with strong representation ability of deep structures have ever increasing popularity in many research areas. The main difference of Convolutional Neural Networks with respect to existing similar ...
Highlights- A novel convolution technique named as Differential Convolution is proposed.
- ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2016
242 pages
ISBN:9781450347860
DOI:10.1145/2967413
Copyright © 2016 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 12 September 2016
Check for updates
Qualifiers
- Short-paper
- Research
- Refereed limited
Conference
ICDSC '16
ICDSC '16: 10th international conference on distributed smart camera
September 12 - 15, 2016
Paris, France
Acceptance Rates
Overall Acceptance Rate 92 of 117 submissions, 79%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 47Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 01 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in