Advertisement

Abstract

To build an intelligent robot, we must develop an autonomous mental development system that incrementally and speedily learns from humans, its environments, and electronic data. This paper presents an ultra-fast, multimodal, and online incremental transfer learning method using the STAR-SOINN. We conducted two experiments to evaluate our method. The results suggest that recognition accuracy is higher than the system that simply adds modalities. The proposed method can work very quickly (approximately 1.5 [s] to learn one object, and 30 [ms] for a single estimation). We implemented this method on an actual robot that could estimate attributes of “unknown” objects by transferring attribute information of known objects. We believe this method can become a base technology for future robots.

SOINN is an unsupervised online-learning method capable of incremental learning. By approximating the distribution of input data and the number of classes, a self-organized network is formed. SOINN offers the following advantages: network formation is not required to be predetermined beforehand, high robustness to noise, and reduced computational cost. In the near future, a SOINN device will accompany an individual from birth; this will allow the agent to share personal histories with its owner. In this occasion, a person’s SOINN will know "everything" about its owner, lending assistance at any time and place throughout one’s lifetime. Besides having a personal SOINN, an individual can install this self-enhanced agent into human-made products - making use of learned preferences to make the system more efficient. If deemed non-confidential, an individual’s SOINN could also autonomously communicate another SOINN to share information.

Keywords

SOINN (Self-organizing Incremental Neural Network) Home robots Machine learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kimura, D., Pichai, K., Kawewong, A., Hasegawa, O.: Ultra-fast and online incremental transfer learning. In: The 17th Symposium on Sensing via Image Information, Kanagawa, Japan (June 2011) (in Japanese)Google Scholar
  2. 2.
    Shen, F., Hasegawa, O.: A fast nearest neighbor classifier based on self-organizing incremental neural network. Neural Netw. 21(10), 1537–1547 (2006)CrossRefGoogle Scholar
  3. 3.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)Google Scholar
  4. 4.
    Kawewong, A., Hasegawa, O.: Fast and incremental attribute transferring and classifying system for detecting unseen object classes. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part III. LNCS, vol. 6354, pp. 563–568. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  5. 5.
    Araki, T., Nakamura, T., Nagai, T., Funakoshi, K., Nakano, M., Iwahashi, N.: Autonomous acquisition of multimodal information for online object concept formation by robots. In: 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1540–1547 (September 2011)Google Scholar
  6. 6.
    Bosch, A., Zisserman, A., Munoz, X.: Representing shape with a spatial pyramid kernel. In: Proceedings of the 6th ACM International Conference on Image and Video Retrieval, CIVR 2007, pp. 401–408. ACM, New York (2007)Google Scholar
  7. 7.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 886–893 (June 2005)Google Scholar
  8. 8.
    Haasch, A., Hofemann, N., Fritsch, J., Sagerer, G.: A multi-modal object attention system for a mobile robot. In: Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Edmonton, Alberta, Canada, pp. 1499–1504. IEEE (August 2005)Google Scholar
  9. 9.
    Kimura, D., Pichai, K., Hasegawa, O.: Ultra-fast and online incremental transfer learning with the internet. In: The 18th Symposium on Sensing via Image Information, Kanagawa, Japan (June 2012) (in Japanese)Google Scholar
  10. 10.
    Kimura, D., Pichai, K., Hasegawa, O.: Unknown object recognition by images on the internet using ultra-fast and online incremental transfer learning. In: Meeting on Image Recognition and Understanding, Fukuoka, Japan (August 2012) (in Japanese)Google Scholar
  11. 11.
    Kumar, N., Berg, A.C., Belhumeur, P.N.: Shree K. Nayar. Attribute and simile classifiers for face verification. In: IEEE International Conference on Computer Vision (ICCV) (October 2009)Google Scholar
  12. 12.
    Nakamura, T., Nagai, T., Iwahashi, N.: Multimodal object categoriza-tion by a robot. In: Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2415–2420 (2007)Google Scholar
  13. 13.
    Ozasa, Y., Iwahashi, N., Takiguchi, T., Ariki, Y., Nakano, M.: Integrated multimodal information for detection of unknown objects and unknown names. In: 2012 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (March 2012)Google Scholar
  14. 14.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. on Knowl. And Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  15. 15.
    Rohrbach, M., Stark, M., Szarvas, G., Gurevych, I., Schiele, B.: What helps where – and why? semantic relatedness for knowledge transfer. In: CVPR (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Osamu Hasegawa
    • 1
  • Daiki Kimura
    • 1
  1. 1.Tokyo Institute of TechnologyJapan

Personalised recommendations