A Fast Training Algorithm of Multiple-Timescale Recurrent Neural Network for Agent Motion Generation
Pages 243 - 246
Abstract
Motion understanding and regeneration are two basic aspects of human-agent interaction. One important function of agents is to represent human's activities. For better interaction with human, robot agents should not only do something following human's order, but also be able to understand or even play some actions. Multiple Timescale Recurrent Neural Networks (MTRNN) is believed to be an efficient tool for robots action generation. In our previous work, we extended the concept of MTRNN and developed Supervised MTRNN for motion recognition. In this paper, we use Conditional Restricted Boltzmann Machine (CRBM) to initialize Supervised MTRNN and accelerate the training speed of Supervised MTRNN. Experiment results show that our method can greatly increase the training speed without losing much performance.
References
[1]
Tsai T., Hsu Y., Ma A., King T., and Wu C. Developing a telepresence robot for interpersonal communication with the elderly in a home environment. Telemedicine and e-Health 13, 4 (2007), 407--424.
[2]
Sekiguchi D., Inami M., and Tachi S. Robotphone: RUI for interpersonal communication. In Proc. Of CHI EA '01, ACM Press (2001), 277--278.
[3]
Yamashita Y. and Tani J. (2008). Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment, PLoS Computational Biology 4 (11).
[4]
Yu Z. and Lee. M. Human Motion Based Intent Recognition Using a Deep Dynamic Neural Model. Robotics and Autonomous System, Neural Networks, Volume 69. 2015.09
[5]
Funahashi K., Nakamura Y. (1993). Approximation of dynamical systems by continuous time recurrent neural networks. Neural Networks, 6(6):801--806.
[6]
Bottou, L. (2004). "Stochastic Learning". Advanced Lectures on Machine Learning. LNAI 3176, Springer Verlag. pp. 146--168. ISBN 978-3-540-23122-6
[7]
Taylor, G., Hinton, G. and Roweis, S. (2007). Modeling human motion using binary latent variables. Proc. NIPS 19 (pp. 1345--1352).
Index Terms
- A Fast Training Algorithm of Multiple-Timescale Recurrent Neural Network for Agent Motion Generation
Recommendations
A stable online self-constructing recurrent neural network
ISNN'11: Proceedings of the 8th international conference on Advances in neural networks - Volume Part IIIA new online self-constructing recurrent neural network (SCRNN) model is proposed, of which the network structure could adjust according to the specific problem in real time. If the approximation performance of SCRNN is insufficient, SCRNN can create ...
A new type of recurrent neural network for handwritten character recognition
ICDAR '95: Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1The authors propose a new type of recurrent neural network for handwritten character recognition. The proposed recurrent neural network differs from Jordan and Elman recurrent neural networks in view of functions and architectures because it was ...
A new type of recurrent neural network for handwritten character recognition
ICDAR '95: Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1The authors propose a new type of recurrent neural network for handwritten character recognition. The proposed recurrent neural network differs from Jordan and Elman recurrent neural networks in view of functions and architectures because it was ...
Comments
Information & Contributors
Information
Published In
October 2015
254 pages
ISBN:9781450335270
DOI:10.1145/2814940
- General Chairs:
- Minho Lee,
- Takashi Omori,
- Program Chairs:
- Hirotaka Osawa,
- Hyeyoung Park,
- James Young
Copyright © 2015 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].
Sponsors
- BESK: Brain Engineering Society of Korea
In-Cooperation
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 October 2015
Check for updates
Author Tags
Qualifiers
- Research-article
Conference
HAI 2015
Sponsor:
- BESK
HAI 2015: The Third International Conference on Human-Agent Interaction
October 21 - 24, 2015
Kyungpook, Daegu, Republic of Korea
Acceptance Rates
Overall Acceptance Rate 121 of 404 submissions, 30%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 79Total Downloads
- Downloads (Last 12 months)1
- 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