Bachelor/Masterseminar (WS 2017/2018)

General Information

• This seminar is open for bachelor- and master students.
• You find administrative information at UnivIS.
• Participants should sign up for the course in the virtual campus.
• The course is usually offered in the winter term.

Topic: Künstliche Intelligenz - gestern, heute, morgen.

Gemeinsames Seminar mit Smart Environments (für BA und MA offen).

Künstliche Intelligenz (KI) ist der Teil der Informatik, in dem Algorithmen für solche Bereiche entwickelt und erforscht werden, in denen Menschen noch besser sind als Standard-Programme. Lange Zeit galt dies beispielsweise für Schach -- bis zum Durchbruch 1996, als Deep Blue den damaligen Großmeister Kasparov besiegte. Künstliche Intelligenz Forschung verfolgt einerseits ein ingenieurswissenschaftliches Ziel  -- das heisst, die Entwicklung von funktionalen und effizienten Algorithmen. Zum anderen wird ein erkenntnistheoretisches Ziel verfolgt: Wer KI Programme entwickelt, hat häufig den Anspruch, dass diese Programme auf der menschlichen Kognition verwandten Prinzipien basieren. Im Seminar werden wir uns anhand von Originalarbeiten mit den zentralen Ansätzen der KI auseinandersetzen. Dabei werden wir uns für jedes Thema sowohl mit den ersten Grundlagenarbeiten als auch mit aktuellen Weiterentwicklungen auseinandersetzen und diskutieren, wie sich diese Themengebiete in zukünftigen Anwendungen einsetzen lassen.

Recommended Reading / Links 

Wissensrepräsentation

• Palmer, S. (1978). Fundamental aspects of cognitive representation.
• Brachman, R. J., & Schmolze, J. G. (1985). An Overview of the KL‐ONE Knowledge Representation System*. Cognitive science, 9(2), 171-216.
• Krzysztof Janowicz, Frank van Harmelen, James A. Hendler, Pascal Hitzler: Why the Data Train Needs Semantic Rails.AI Magazine 36(1): 5-14 (2015)

Problemlösen und Planen

• Newell, A., Shaw, J. C., & Simon, H. A. (1959, January). Report on a general problem-solving program. In IFIP Congress (pp. 256-264).
• Green, C. (1969). Application of theorem proving to problem solving (No. SRI-TR-4). SRI INTERNATIONAL MENLO PARK CA ARTIFICIAL INTELLIGENCE CENTER.
• Fikes, R. E., & Nilsson, N. J. (1972). STRIPS: A new approach to the application of theorem proving to problem solving. Artificial intelligence, 2(3), 189-208.
• Haslum, P., & Geffner, H. (2014, May). Heuristic planning with time and resources. In Sixth European Conference on Planning.

Maschinelles Lernen

• Michalski, R. S., Carbonell, J. G., & Mitchell, M. L. (1986). An Artificial Intelligence Approach. Understanding the Nature of Learning, 2, 3-26.
• Muggleton, S. (1991). Inductive logic programming. New generation computing, 8(4), 295-318.
• Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural computation, 18(7), 1527-1554.

Presentations:

• Cognitive Artificial Intelligence
  1. Human vs. machine learning [pdf]
  2. Learning and reasoning by analogy [pdf]
  3. Incorporating (re)-interpretation in case-based reasoning [pdf]
  4. The teachable language comprehender: A simulation program and theory of language [pdf]
• Knowledge Representation for Scene Understanding
  1. Scene Interpretation with Description Logics
  2. Context-aware classification for incremental scene interpretation
  3. Image Understanding Using Qualitative Geometry and Mechanics
  4. Textonboost for image understanding
• Machine Learning – Basic Approaches
  1. Induction of decision trees [pdf]
  2. Do we need hundreds of classifiers to solve real world classification problems [pdf]
  3. Machine learning and data mining [pdf]
  4. Temporal difference learning and TD-Gammon [pdf]
• Machine Learning and Games
  1. Fluxplayer: A successful general game player
  2. Alpha-beta search enhancements
  3. Evolving strategy for a probabilistic game of imperfect information
  4. Lifelong robot learning
• Deep Learning
  1. Introduction to Deep Learning [pdf]
  2. A unified architecture for natural language processing
  3. The Arcade Learning Environment: An Evaluation Platform for General Agents
  4. Deep reinforcement learning from self-play in imperfect-information game
• Planning for Intelligent Robots
  1. Generative adversarial nets [pdf]
  2. Shared grounding of event descriptions by autonomous robots
  3. Fast Planning Through Planning Graph Analysis
  4. Path Planning for Autonomous Underwater Vehicles
• Selected Applications of Machine Learning
  1. Visual Learning of Arithmetic Operation [pdf]
  2. Automatic analysis of facial actions [pdf]
  3. Thumbs up?: sentiment classification using machine learning techniques [pdf]
  4. Knowledge acquisition with forgetting: an incremental and developmental setting [pdf]
• Autonomous Cars
  1. Robust Vehicle Localization in Urban Environments Using Probabilistic Maps
  2. The dynamic window approach to collision avoidance
  3. The robot that won the DARPA Grand Challenge
• White-Box Learning and Explainability
  1. Why should i trust you?: Explaining the predictions of any classifier [pdf]
  2. Interpretable decision sets: A joint framework for description and prediction [pdf]
  3. Inductive logic programming [pdf]
• Interaction and Language
  1. A Computational Model of Human-Robot Spatial Interactions Based on a Qualitative Trajectory Calculus
  2. Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation
  3. Deep Semantic Analysis of Text
• Selected AI Applications
  1. Plane-based object categorisation using relational learning
  2. Reinforcement Learning Produces Dominant Strategies for the Iterated Prisoner's Dilemma [pdf]
  3. AutoTutor: An intelligent tutoring system with mixed-initiative dialogue [pdf]
  4. Human activity recognition using wearable sensors [pdf]

Previous Seminars

KI-Seminare:  [WS 16/17] [WS 15/16]

Bachelor Seminare: [WS 04/05] [WS 05/06] [WS 06/07] [<link kogsys/teaching/archiv/ws0708/bachelorseminar_kognitive_systeme/ - extern>WS 07/08</link>] [<link kogsys/teaching/archiv/ws0809/bachelorseminar_kognitive_systeme/ - extern>WS 08/09</link>] [WS 09/10]  [WS 10/11]    [SS 11] [WS 11/12] [WS 12/13] [WS13/14]

Master Seminare: [SS 05] [SS 06] [SS 08] [SS 09] [WS 09/10] [SS 10]  [WS 11/12] [WS 12/13] [WS 13/14]

Reading Clubs:

• WS 14/15: Cognitive Models for Number Series Induction Problems  [Archiv Page]
• SS 2014: Experimenting with a Humanoid Robot - Programming NAO to (Inter-)Act  [Archiv Page] 
• SS 2013: An introduction into statistic data analysis with R  [Archiv Page] 
• SS 2012: Transfer Learning  [Archiv Page] 
• SS 2011: Emotion Mining in Images and Text  [Archiv Page] 
• SS 2010: Aspects of Cognitive Robotics [Archiv Page] 
• SS 2009: Reading Club Decision Support Systems [Archiv Page] 
• WS 08/09: Algebraic Foundations of Functional Programming (together with Theoretical Computer Science) [Archiv Page]  
• SS 2008: Similarity (together with Statistics) [Archiv Page]
• SS 2007: Automated Theorem Proving with Isabelle (together with Theoretical Computer Science) [Archiv Page]
• SS 2006: Support Vector Machines [Archiv Page]