AI
COMP 1010 Home > More About Computer Science
|
IntroductionArtificial Intelligence is the study of how computer systems can simulate intelligent processes such as learning, reasoning, and understanding symbolic information. This is a multidisciplinary field, having close connections to psychology, engineering, mathematical logic, neurosciences and biology, is generally viewed as a specialty of computer science. AI techniques and methodologies include learning, intelligent agents, knowledge representation, logic programming, and planning. Some AI Applications include electronic commerce, intelligent tutoring systems, knowledge management, performance management and exploratory vision. Presented here are a couple of interesting research areas in the field of Artificial Intelligence.
|
|---|
{{{Body}}}
Anti Spam Research
The goal of AI in this research is to stop spam for users of the Internet at large. Unwanted communication, especially unsolicited commercial communication is the bane of the Internet. The same technology that in so many is of benefit to society is also the technology that can overwhelm someone with offensive messages.
This is a complicated problem, and while existing technologies can reduce spam, none is a panacea for spam. This will be a hot topic of research for years to come.
Computer Vision
Research is currently being done on multi scale human perception system called PeopleVision (IBM). This research is also specializes in biometrics, which is identifying people by their fingerprints or facial characteristics. Work is also being done on video browsing using closed caption text, speech recognition, camera motion and face finding.
Personal Wizards
This is an approach to capturing know-how of computer-based procedures by combining recordings of experts performing a task. Collaborative programming-by-demonstration (PBD} is a way of developing rich procedure models by recording how one or more experts interact with an application while performing a specific task, and combining these recordings into an executable, distributable model via an appropriate learning algorithm. Collaborative PBD therefore extends traditional PBD by learning from multiple demonstrations and combining the collective knowledge of multiple experts.
References and Useful Links
http://www.cs.umanitoba.ca/newsite/research.html
http://domino.research.ibm.com/comm/research.nsf/pages/r.ai.html
