April 9, 2012
School of Biotechnology, Amritapuri
Through the holding of hands and sharing of experiences, new horizons of knowledge will open in the highest realms of science and technology to those thirsting for knowledge in India and others parts of the world—especially to students, teachers and researchers.
- Chancellor Amma
Research teams from India and Italy will come together to work on a project funded by the Department of Science and Technology, Government of India.
Italian universities including University of Milan, University of Pavia and Italian Institute of Technology will join hands with Amrita to investigate a cerebellum-inspired approach for pattern classification in robots.
“Recent successes in machine learning and robotics have expanded the robotic applications. Nevertheless, both robotics and machine learning still have a long way to go, as far as adopting bio-inspired approaches,” explained Dr. Shyam Diwakar, Assistant Professor, who will lead the project on the Amrita side.
Dr. Shyam leads all research efforts at the Amrita Lab for Computational Neurosciences.
Explaining the project goal, he said, “Decades of research into the structure and function of the cerebellum have led to some understanding of how learning takes place. There are many theories on what signals the cerebellum operates on, and how it works in concert with other parts of the central nervous system. Computational cerebellar models built with this knowledge are being applied for controlling robotic dynamics. This research worldwide is in its infancy stage.”
Elaborating further, he added, “In this joint venture, we will develop a cerebellum inspired pattern recognition algorithm for robotic data classification. We will investigate the temporal and spatial dynamics in the cerebellar network models capable of predicting cerebellar input-output transformations by analyzing the mathematical and computational properties of the network.”
“The cerebellum has long been known for its role in movement and articulation. Cerebellar motor articulation control algorithms have existed for more than 35 years although such methods do not faithfully reproduce cerebellar architecture,” he further added.
“We will exploit biophysical neural network models to solve the problems of pattern recognition and navigation in mobile robots to achieve practical algorithms for surgery or disaster mitigation. This project will rely on biological basis for design and function of a pattern classifier that can be used in motor articulation,” he underlined.
The project will not only allow technology transfer between the two countries but will also support researcher mobility; a maximum of two visits from either side per year will be permitted.
Prof. Egidio D’Angelo, a world-renowned expert on cerebellar physiology from University of Pavio will also be part of the team.
The project is expected to be completed by 2015.