Applied Artificial Intelligence (WS 14/15)

What happened to Artificial Intelligence (AI)? In the 1970s, researchers expected soon machines to be more intelligent than humans thus revolutionizing society and civilization. Only a few years later they had to admit that, for a computer, it is harder to reason like a five-year-old than to play a game of chess. The AI hype burst.

And today? 

Unnoticed (and often not under the keyword "AI"),AI applications have become ubiquitous in our everyday lifes:

  • Speech control in cars, mobile phones, etc.
  • Face recognition in cameras
  • (Learning) Spam classification in e-mail clients
  • AI in computer games
  • Semantic search of the Internet
  • Machine translation services in the Internet
  • Not to speak of numerous professional AI applications as business intelligence, robotics, etc.

 

So, AI applications are relevant - reason enough to offer a course on AI.

AI courses have a long history in Computer Science departments. Many of those courses focus on the theory behind AI. This course "Applied AI" has a different focus: the architecture and development of AI applications with state-of-the-art technology, languages, and tools.

Lectures

Lectures and lab sessions will be interwoven. The lecture is structured as follows (current lecture slides for download):

  1. Introduction
  2. Knowledge Representation
  3. Queries
  4. AI Application Architecture
  5. Information Retrieval
  6. Agents
  7. Natural Language Processing
  8. Machine Learning
  9. Computer Vision
  10. Summary

Video recordings of the lectures under https://lernen.h-da.de/course/view.php?id=2994 , Enrolment key apartinws2014 (login with h_da user id and password)

 

Laboratory

In this course, you will, in teams, implement an AI application for a digital museum and will research and learn all methods and technology necessary.

The lab sessions are interlaced with the lecture (Mo., 12:00 – 15:45 each week)

Please, bring your own notebook if you own one. You need h_da WLAN access.

Assignments:

  1. Introduction
  2. Knowledge Representation
  3. Queries
  4. AI Application Architecture
  5. Information Retrieval
  6. Agents
  7. Natural Language Processing
  8. Machine Learning
  9. Computer Vision
  10. Summary

 

Material

 

Examination

Schedule for oral exams.