Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
team:daniel_nyga [2013/09/09 09:57] – nygateam:daniel_nyga [2016/11/07 09:25] – [Supervised Theses] nyga
Line 1: Line 1:
 ~~NOTOC~~ ~~NOTOC~~
 =====Daniel Nyga, M.Sc. (TUM)====== =====Daniel Nyga, M.Sc. (TUM)======
-^ {{:wiki:daniel_nyga.jpg}} ||||+| {{:wiki:daniel_nyga.jpg?0x180}} ||||
 |::: ||Research Staff\\ \\ || |::: ||Research Staff\\ \\ ||
 |:::|Room: |1.77| |:::|Room: |1.77|
Line 8: Line 8:
 |:::|Mail: |<cryptmail>nyga@cs.uni-bremen.de</cryptmail>| |:::|Mail: |<cryptmail>nyga@cs.uni-bremen.de</cryptmail>|
 |:::| || |:::| ||
 + 
 ====About==== ====About====
 Before I joined the Institute for Artificial Intelligence, I studied Computer Science at Technische Universität München, where I received my Master's degree in 2010 (with distinction). In February 2011 I started my PhD supervised by Prof. Michael Beetz at the //Intelligent Autonomous Systems// group at TUM, which I am now continuing at the IAI, University of Bremen. Before I joined the Institute for Artificial Intelligence, I studied Computer Science at Technische Universität München, where I received my Master's degree in 2010 (with distinction). In February 2011 I started my PhD supervised by Prof. Michael Beetz at the //Intelligent Autonomous Systems// group at TUM, which I am now continuing at the IAI, University of Bremen.
Line 19: Line 19:
  
 Knowledge about actions and objects is represented as //Probabilistic Robot Action Cores (PRAC)//, which can be thought of generic event patterns that enable a robot to infer important information that is missing in an original natural-language instruction. PRAC models are represented in //Markov Logic Networks//, a powerful knowlegde represenation formalism combing first-order logic and probability theory. Knowledge about actions and objects is represented as //Probabilistic Robot Action Cores (PRAC)//, which can be thought of generic event patterns that enable a robot to infer important information that is missing in an original natural-language instruction. PRAC models are represented in //Markov Logic Networks//, a powerful knowlegde represenation formalism combing first-order logic and probability theory.
 +
 +I am involved in the European research projects [[http://www.youtube.com/watch?v=qQG3CkH27qc#t=118|RoboHow]] ([[http://www.robohow.org]]) and [[http://www.acat-project.eu|ACAT]].
 +
 +I am also the lead developer in the projects [[http://www.pracmln.org|pracmln]] and [[http://www.open-ease.org/nlp-overview/|PRAC]].
  
 If you are interested in a student project in any of the above topics, please contact me via E-Mail or just drop into my office.  If you are interested in a student project in any of the above topics, please contact me via E-Mail or just drop into my office. 
 +
 +
  
 ====Fields of Interest==== ====Fields of Interest====
   * Artificial Intelligence   * Artificial Intelligence
 +  * Probability Theory
   * Probabilistic Knowledge Processing   * Probabilistic Knowledge Processing
   * Machine Learning   * Machine Learning
Line 32: Line 39:
  
 ====Teaching==== ====Teaching====
 +  * AI: Knowledge Acquisition and Representation ([[https://ai.uni-bremen.de/teaching/le-ki2-ws15|WS2015/16]]) (Lecturer)
 +  * Foundations of Artificial Intelligence ([[https://ai.uni-bremen.de/teaching/le-ai-ss15|SS2015]]) (Tutorial/Co-Lecturer)
 +  * AI: Knowledge Acquisition and Representation ([[https://ai.uni-bremen.de/teaching/le-ki2-ws14|WS2014/15]]) (Lecturer)
 +  * Foundations of Artificial Intelligence ([[https://ai.uni-bremen.de/teaching/kiss2014|SS2014]]) (Tutorial)
 +  * AI: Knowledge Acquisition and Representation ([[https://ai.uni-bremen.de/teaching/ki2-2013|WS2013/14]]) (Co-Lecturer)
   * Foundations of Artificial Intelligence ([[https://ai.uni-bremen.de/teaching/kiss2013|SS2013]]) (Tutorial)   * Foundations of Artificial Intelligence ([[https://ai.uni-bremen.de/teaching/kiss2013|SS2013]]) (Tutorial)
-  * Technical Cognitive Systems (Lecture & Tutorial, @TUM) ([[https://ias.cs.tum.edu/teaching/ss2012/techcogsys|SS2012]]) +  * Technical Cognitive Systems (Lecture & Tutorial, at TUM) ([[https://ias.cs.tum.edu/teaching/ss2012/techcogsys|SS2012]]) 
-  * Techniques in Artificial Intelligence (Tutorial, @TUM) ([[https://ias.cs.tum.edu/teaching/ws2011/240927786|WS2011/12]]) +  * Techniques in Artificial Intelligence (Tutorial,  at TUM) ([[https://ias.cs.tum.edu/teaching/ws2011/240927786|WS2011/12]]) 
-  * Discrete Probability Theory (Tutorial, @TUM) ([[http://www14.in.tum.de/lehre/2011SS/dwt/|SS2011]]) +  * Discrete Probability Theory (Tutorial, at TUM) ([[http://www14.in.tum.de/lehre/2011SS/dwt/|SS2011]]) 
 + 
 ====Supervised Theses==== ====Supervised Theses====
 +  * Lifelong Learning of First-order Probabilistic Models for Everyday Robot Manipulation (Master's Thesis, Marc Niehaus)
 +  * Scaling Probabilistic Completion of Robot Instructions through Semantic Information Retrieval (Master's Thesis, Sebastian Koralewski)
 +  * To see what no robot has seen before - Recognizing objects based on natural-language descriptions (Master's Thesis, Mareike Picklum)
   * Web-enabled Learning of Models for Word Sense Disambiguation (Bachelor Thesis, Stephan Epping)   * Web-enabled Learning of Models for Word Sense Disambiguation (Bachelor Thesis, Stephan Epping)
-  * Grounding Words to Objects: A Joint Model for Co-reference and Entity Resolution Using Markov Logic Networks for Robot Instruction Processing (Diploma Thesis, Florian Meyer) +  * Grounding Words to Objects: A Joint Model for Co-reference and Entity Resolution Using Markov Logic Networks for Robot Instruction Processing (Diploma Thesis, Florian Meyer)  
- +  
-====Open Positions==== +
-Studentische Hilfskraft im Bereich Wissensrepräsentation und  +
-Sprachverstehen für intelligente autonome Roboter gesucht. +
- +
-Im Rahmen des europäischen Forschungsprojektes RoboHow.Cog [1,2]  +
-werden Methoden erforscht, um Wissen aus unterschiedlichen Quellen  +
-(z.B. Videos, Text, Computerspiele und kinästhetische Demonstration)  +
-miteinander zu verknüpfen, um mobile Haushaltsroboter zu befähigen,  +
-selbstständig ihr Repertoire an Fähigkeiten (wie z.B. die  +
-Zubereitung von Pfannkuchen) zu erweitern.  +
- +
-Die Arbeitsgruppe für Künstliche Intelligenz (ai.uni-bremen.de) der  +
-Uni Bremen sucht ab sofort eine studentische Hilfskraft für die  +
-Entwicklung und Integration von probabilistischen Methoden der KI,  +
-die es autonomen Haushaltsrobotern ermöglichen, natürlichsprachliche  +
-Instruktionen aus Rezepten im World Wide Web zu verstehen und  +
-auszuführen. +
- +
-Die HiWi-Tätigkeit kann auch als Ausgangspunkt für weitere Bachelor-,  +
-Diplom- oder Masterarbeiten dienen. +
- +
-Aufgaben: +
-  * Implementierung einer Schnittstelle für das Robot Operating System (ROS), +
-  * Anbindung der Wissensbasis an das Ausführungsmodul des Roboters +
-  * Unterstützung der wissenschaftlichen Mitarbeiter bei der Erweiterung und Integration der Roboterplattform PR2. +
- +
-Kompetenzen: +
-  * Informatikstudium (Bachelor, Master oder Diplom) +
-  * Grundkenntnisse im Bereich Künstliche Intelligenz +
-  * Grundkenntnisse im Bereich Wahrscheinlichkeitstheorie +
-  * Grundkenntnisse im Bereich Maschinelles Lernen +
-  * Programmierkenntnisse in den Sprachen Python u. Java +
- +
-Ausgeschriebene Stundenzahl: 10-20 Std./Woche +
- +
-[1] www.robohow.eu\\ +
-[2] http://www.youtube.com/watch?v=0eIryyzlRwA +
- +
 ====== Publications ====== ====== Publications ======
  
- Impressum - Datenschutz



Prof. Dr. hc. Michael Beetz PhD
Head of Institute

Contact via
Andrea Cowley
assistant to Prof. Beetz
ai-office@cs.uni-bremen.de

Discover our VRB for innovative and interactive research


Memberships and associations:


Social Media: