campUAS

Course Content

• Symbolic AI [1]
  
  • Concept of Agents in AI
  • Problem solving by searching
  • Logic and Reasoning 
• Statistical Learning
  
  • The students gain a principal basic understanding of the mathematical and epistemological basics of statistical learning theory and machine learning.
  • Basic Model of Statistical Learning following [2]
  • Different models such as random Forests, Neural SVMs, and Networks as black boxes
  • Generative Applications / Sampling basics of Text and Image Generation, n-gram Models, GANs
  • Training, testing, validation incl. Overfitting, Test-Train-Split, FP-FN-Tradeoff, ROC-Curves, F1-Score
• Reinforcement Learning
  
  • The students gain a basic understanding of the concept of autonomous and adaptive agents in AI [3]. This includes an overview of established problem modeling frameworks and algorithmic approaches to implementing RL agents.
• Ethical implications for society, principal problems of algorithmic decisions (Information privacy, individual freedom, checks-and balances of citizens, corporations, states etc.)
  
• The students have the opportunity to test their knowledge with prototypes in the exercises
  

Upon completion of the module the student is able to

• Understand the terminology used in modern artificial intelligence including symbolic artificial intelligence, expert-base systems, reasoning, (un- and supervised) statistical learning and reinforcement learning
  
• understand the core concepts of artificial intelligence focusing on the practical level, including primarily testing, validation and interpretation
  
• realize a realistic small application using existing frameworks 
  
• validate the application’s AI model
  
• explain and interpret a model’s predictions properly
  
• are able to assess the ethical and societal dimensions of applications