CALD Seminar

  • David Stork
  • Chief Scientist of Ricoh Silicon Valley and Consulting Associate Professor of Electrical Engineering at Stanford University

The Open Mind Initiative: A collaborative framework for collecting and learning netizen contributions to open source 'intelligent' software

The Open Mind Initiative is a collaborative framework for developing "intelligent" software (e.g., speech recognition, handwriting recognition, common sense

reasoning, ...) over the internet. While based on traditional open source methodology, Open Mind differs in its reliance on large numbers of non-specialist 'netizens' to provide raw data; there are many incentives for netizens to so contribute.

This talk begins by examining several important trends that underly Open Mind:

* the rise in open source software
* the expansion in opportunities for less-skilled users to contribute
* the increase in scientific collaboration over the internet
* the growing need for large sets of lq informalq data from non-experts
* the growing need for lq intelligentq software

Drawing upon the theory of machine learning, pattern recognition and techniques from experimental psychology, we discuss interactive methods for insuring high quality data, even from a large heterogeneous population of contributors. Next we discuss the relation of Open Mind to traditional open source and to data mining. Then we discuss sample projects, including three component projects currently committed, and conclude with a vision of future directions and opportunities.

For More Information, Please Contact: 
Catherine Copetas, copetas@cs.cmu.edu