Incremental training of CNNs for user customization: work-in-progress
Authors: 
Mansureh S. Moghaddam, Barend Harris, Duseok Kang, Inpyo Bae, Euiseok Kim, Hyemi Min, Hansu Cho, Sukjin Kim, Bernhard Egger, Soonhoi Ha, Kiyoung ChoiAuthors Info & Claims
Mansureh S. Moghaddam, Barend Harris, Duseok Kang, Inpyo Bae, Euiseok Kim, Hyemi Min, Hansu Cho, Sukjin Kim, Bernhard Egger, Soonhoi Ha, Kiyoung ChoiAuthors Info & ClaimsArticle No.: 9, Pages 1 - 2
Abstract
This paper presents a convolutional neural network architecture that supports transfer learning for user customization. The architecture consists of a large basic inference engine and a small augmenting engine. Initially, both engines are trained using a large dataset. Only the augmenting engine is tuned to the user-specific dataset. To preserve the accuracy for the original dataset, the novel concept of quality factor is proposed. The final network is evaluated with the Caffe framework, and our own implementation on a coarse-grained reconfigurable array (CGRA) processor. Experiments with MNIST, NIST'19, and our user-specific datasets show the effectiveness of the proposed approach and the potential of CGRAs as DNN processors.
References
[1]
D. C. Ciresan, U. Meier, L. M. Gambardella, and J. Schmidhuber. 2011. Convolutional Neural Network Committees for Handwritten Character Classification. In 2011 International Conference on Document Analysis and Recognition. 1135--1139.
[2]
Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.
[3]
Zhizhong Li and Derek Hoiem. 2016. Learning Without Forgetting. Springer International Publishing, Cham, 614--629.
[4]
Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http://pjreddie.com/darknet/. (2013--2016).
[5]
David Saad (Ed.). 1998. On-line Learning in Neural Networks. Cambridge University Press, New York, NY, USA.
[6]
Yuan-Yuan Shen and Cheng-Lin Liu. 2016. Incremental Learning Vector Quantization for Character Recognition with Local Style Consistency. Springer International Publishing, Cham, 228--239.
[7]
Dongkwan Suh, Kiseok Kwon, Sukjin Kim, Soojung Ryu, and Jeongwook Kim. 2012. Design space exploration and implementation of a high performance and low area Coarse Grained Reconfigurable Processor. In International Conference on Field-Programmable Technology (FPT). 67--70.
Recommendations
Architectures and algorithms for user customization of CNNs
ASPDAC '18: Proceedings of the 23rd Asia and South Pacific Design Automation ConferenceIn this paper we present a convolutional neural network architecture that supports user customization through incremental transfer learning. The architecture consists of a large basic inference engine and a small augmenting engine. After training the ...
Architectures and algorithms for on-device user customization of CNNs
AbstractA convolutional neural network (CNN) architecture supporting on-device user customization is proposed. The network architecture consists of a large CNN trained on a general data and a smaller augmenting network that can be re-trained ...
Highlights- A novel CNN-based network architecture is proposed to enable user specialization.
FPGA-based low-batch training accelerator for modern CNNs featuring high bandwidth memory
ICCAD '20: Proceedings of the 39th International Conference on Computer-Aided DesignTraining convolutional neural networks (CNNs) requires intensive computations as well as a large amount of storage and memory access. While low bandwidth off-chip memories in prior FPGA works have hindered the system-level performance, modern FPGAs ...
Comments
Information & Contributors
Information
Published In
October 2017
51 pages
ISBN:9781450351843
DOI:10.1145/3125501
Copyright © 2017 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 the author(s) 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: 15 October 2017
Check for updates
Qualifiers
- Research-article
Funding Sources
- National Research Foundation (NRF) of Korea
- Seoul National University
Conference
ESWEEK'17
Acceptance Rates
Overall Acceptance Rate 52 of 230 submissions, 23%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 103Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)1
Reflects downloads up to 08 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