TX EduXpert - шаблон joomla Новости


Za SlitSlider

Energized interaction with Kurita machine learning Laboratory.

Hands together for smarter machines.

Hottest topics that require bright brains.

Mastering the master.

we always Aim High.
Разработка и создание интернет магазина Joomla

Our Message (EN)

Future computer programs will contain a growing part of 'intelligent' software modules that are not conventionally programmed, but that are learned either from data provided by the user or from data that the program autonomously collects during its use. In this spirit, the Machine Learning Lab deals with research on Machine Learning techniques and the integration of learning modules into larger software systems, aiming at their effective application in complex real-world problems. Application areas are robotics, control, forecasting and disposition systems, scheduling and related fields. Machine learning and Pattern recognition laboratory in Hiroshima university is led by Prof. Takio Kurita. He received the B.Eng. degree from Nagoya Institute of Technology and the Dr. Eng. degree from the University of Tsukuba, in 1981 and in 1993, respectively. He joined the Electrotechnical Laboratory, AIST, MITI in 1981. From 1990 to 1991 he was a visiting research scientist at Institute for Information Technology, National Research Council Canada. From 2001 to 2009, he was a deputy director of Nueroscience ResearchInstitute, National Institute of Advanced Industrial Science and Technology (AIST). Also he was a Professor at Graduate School of Systems and Information Engineering, University of Tsukuba from 2002 to 2009. He is currently a Professor at Hiroshima University. His current research interests include statistical pattern recognition and its applications to image recognition. He is a member of the IEEE, the IPSJ, the IEICE of Japan, Japanese Neural Network Society, The Japanease Societey of Artificial Intelligence.


Our research topics are categorized under the following areas:

  • The Machine Learning lab was setup to study theoretical and applied aspects of Machine Learning in various domains. We are interested in : 
  • Large Scale convex optimization for learning problems,
  • Multiple Kernel Learning 
  • Robust decision making under uncertainty
  • Bayesian Nonparametrics 
  • Low-rank Matrix Estimation
    We are actively pursuing applications in the area of :
  • Computational Biology,
  • Object Detection in Images,
  • Video Segmentation and Summarization,
  • Detection of rare topics in text documents
  • Statistical modeling of Computer Systems