MTV/Publications/Tutorials

Data Mining and Learning

Data Mining and Learning for Test and Verification Applications

Detail of the project is given on this password-protected page which is currently for internal use only. We are still in the initial investigation phase for most of the problems and hence there is not much material to be publicized at this point.

We expect public material be available starting from the summer, 2006.

(still under construction ...) Last update: 01/24/2006 10:45:07 AM

In our group, we focus on applying various data mining and learning techniques to test and verification related applications. For example, currently we have two projects funded by Semiconductor Research Corporation (SRC):

Task ID 1173.001 - Statistical Timing Simulation Tools and Methodologies for Speed Test and Performance Validation
Task ID 1360.001 - Simulation Data Mining for Functional Test Pattern Generation

The key is to understand what mining and learning techniques are available and what the potentials are for these techniques to be applied in design and manufacturing. We divide the techniques into four categories: Association rule analysis, Computational learning, Machine learning, and Statistical learning and apply them separately in separate problem formulations. Algorithms used in different areas can be dramatically different.

Most of the ideas are still under investigation and hence, there is not much material that we can publicize at this point. If you are our industrial sponsors and would like to know more on the progress of the projects, please feel free to contact us.