Prof. Dr. Kristian Kersting
Computer Science Department and Centre for Cognitive Science, TU Darmstadt
Altes Hauptgebäude, Room 074, Hochschulstrasse 1, 64289 Darmstadt, Germany
kersting _at_, kristian.kersting _at_

Research interests. My team and I in the Machine Learning group would like to make computers learn so much about the world, so rapidly and flexibly, as humans. This poses many deep and fascinating scientific problems: How can computers learn with less help from us and data? How can computers reason about and learn with complex data such as graphs and uncertain databases? How can pre-existing knowledge be exploited? How can computers decide autonomously which representation is best for the data at hand? Can learned results be physically plausible or be made understandable by us? How can computers learn together with us in the loop?

Bio. Kristian Kersting is a Professor (W3) for Machine Learning at the Computer Science Department of the TU Darmstadt University, Germany, where he heads the machine learning lab. He is also a Deputy Director of the Centre for Cognitive Science. After receiving his Ph.D. from the University of Freiburg in 2006, he was with the MIT, Fraunhofer IAIS, the University of Bonn, and the TU Dortmund University, where he was a member of the DFG CRC 876 "Providing Information by Resource-Constrained Data Analysis" and also a Co-Director of the Dortmund Center for Data-Based Media Analysis (DOCMA). His main research interests are statistical relational artificial intelligence (AI), probabilistic deep learning, machine learning, and data mining, as well as their applications. Kristian has published over 160 peer-reviewed technical papers and co-authored a book on statistical relational AI. He received the European Association for Artificial Intelligence (EurAI, formerly ECCAI) Dissertation Award 2006 for the best AI dissertation in Europe, a Fraunhofer Attract Research Grant (2008-2013), two best-paper awards (ECML 2006, AIIDE 2015), one best poster award (GIS 2011), one best presentation award (NC^2 2015), two outstanding PC/reviewer awards (AAAI 2013, ECCV 2016), and a Distinguished Lecturer Award from the University of Jena (2017). Kristian was also an ERCIM Cor Baayen Award 2009 finalist, gave several tutorials at top conferences, co-chaired several international workshops such as BeyondLabeler, BUDA, CMPL, CoLISD, DeLBP, DS+J, MLG, SRL, and SymInfOpt as well as the AAAI Student Abstract track and the Starting AI Research Symposium (STAIRS), and cofounded the international workshop series on Statistical Relational AI (StarAI). He regularly serves on the PC (often at senior level) for several top conference and co-chaired the PC of ECML PKDD 2013 and UAI 2017. He is the Speciality Editor in Chief for Machine Learning and AI of Frontiers in Big Data, and is/was an action editor of TPAMI, JAIR, AIJ, DAMI, and MLJ as well as on the editorial boards of KI, NGC, Information, and Big Data and Cognitive Computing.

2017 - now: Full Professor (W3) for Machine Learning at the CS Department of the TU Darmstadt, Germany
2013 - 2017: Associate Professor (W2) for Data Mining at the CS Department of the TU Dortmund University, Germany
2012 - 2013: Assistant Professor (W1) for Spatio-Temporal Pattern in Agriculture at the Faculty of Agriculture of the University of Bonn, Germany
2008 - 2012: Fraunhofer Attract research group leader at the Fraunhofer IAIS, Germany
2007: PostDoctoral Associate at MIT CSAIL, USA, working with Leslie Kaelbling, Josh Tenenbaum, and Nicholas Roy.
2000 - 2006: Ph.D. student at the CS Department of the University of Freiburg, Germany, working with Luc De Raedt (supervsior) and Wolfram Burgard.
1996 - 2000: Diploma in Computer Science at the CS Department of the University of Freiburg, Germany

P5 Award 2017 of the Alumni Computer Science Dortmund for the Project Group 608 "Manipulation - Development and critical examination of a framework for extracting and transferring semantic information between videos". It is given to student project groups with a high practical relevance.
Distinguished Lecturer Award of the Faculty of Mathematics and Computer Science at the Friedrich-Schiller-University Jena
Outstanding Reviewer Award of the European Conference on Computer Vision (ECCV)
Best Paper Award of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE)
Best Paper Presentation Award of the New Challenges in Neural Computations (NC2) workshop
Outstanding PC Member Award of the AAAI Conference on Artificial Intelligence (AAAI)
Best Poster Award of the ACM SIGSPATIAL Advances in Geographic Information Systems (GIS)
Fraunhofer Attract research grant, the excellence stipend programme of Fraunhofer
European Association for Artificial Intelligence (EurAI, formerly ECCAI) Dissertation Award for the best AI dissertation in Europe
Best Student Paper Award of the European Conference on Machine Learning (ECML)
Wolfgang-Gentner Young Talent Award for an Outstanding Diploma Thesis at the CS Department of the University of Freiburg


Luc De Raedt, Kristian Kersting, Sriraam Natarajan, David Poole (2016): Statistical Relational Artificial Intelligence: Logic, Probability, and Computation. Synthesis Lectures on Artificial Intelligence and Machine Learning, Morgan & Claypool Publishers, ISBN: 9781627058414. This book examines the foundations of combining logic and probability into what are called relational probabilistic models. It introduces representations, inference, and learning techniques for probability, logic, and their combinations.
Christian Bauckhage, Kristian Kersting (2016): Collective Attention on the Web. Foundations and Trends in Web Science 5(1-2):1-136. Understanding the dynamics of collective human attention has been called a key scientific challenge for the information age. Tackling this challenge, this monograph explores the dynamics of collective attention related to Internet phenomena such as Internet memes, viral videos, or social media platforms and Web-based businesses. We discuss mathematical models that provide plausible explanations as to what drives the apparently dominant dynamics of rapid initial growth and prolonged decline.
Jörg Lässig, Kristian Kersting, Katharina Morik (2016): Computational Sustainability. Studies in Computational Intelligence, Vol. 645, Springer, ISBN:978-3-319-31856-1. This editorial book gives an overview of the state of the art research in Computational Sustainability as well as case studies of different application scenarios. This covers topics such as renewable energy supply, energy storage and e-mobility, efficiency in data centers and networks, sustainable food and water supply, sustainable health, industrial production and quality, etc. The book describes computational methods and possible application scenarios.
Jude Shavlik, Kristian Kersting, Sriraam Natarajan, Tushar Khot (2015): Boosted Statistical Relational Learners: From Benchmarks to Data-Driven Medicine. SpringerBrief in Computer Science, 2015, ISBN: 978-3-319-13643-1. This SpringerBrief addresses the challenges of analyzing multi-relational and noisy data by proposing several Statistical Relational Learning (SRL) methods. It reviews the use of functional gradients for boosting the structure and the parameters of statistical relational models. The algorithms have been applied successfully in several SRL settings and have been adapted to several real problems from Information extraction in text to medical problems.
Luc De Raedt, Paolo Frasconi, Kristian Kersting, Stephen Muggleton (2008): Probabilistic Inductive Logic Programming: Theory and Applications. Lecture Notes in Computer Science, Vol. 4911, Springer, ISBN: 978-3-540-78651-1. This editorial book provides an introduction to statistical relational learning with an emphasis on those methods based on logic programming principles. The question of how to combine probability and logic with learning is getting an increased attention as there is an explosive growth in the amount of heterogeneous data that is being collected in the business and scientific world. The structures encountered can be as simple as sequences and trees or as complex as citation graphs, the World Wide Web, and relational databases
Kristian Kersting (2006): An Inductive Logic Programming Approach to Statistical Relational Learning. IOS Press, ISBN: 978-1-58603-674-4. This books addresses Probabilistic Inductive Logic Programming. The new area is closely tied to, though strictly subsumes, a new field known as ‘Statistical Relational Learning’ which has in the last few years gained major prominence in the AI community. The book makes several contributions, including the introduction of a series of definitions which circumscribe the new area formed by extending Inductive Logic Programming to the case in which clauses are annotated with probability values. Also, it introduces Bayesian logic programs and investigates the approach of Learning from proofs and the issue of upgrading Fisher Kernels to Relational Fisher kernels.


Publications can be found at loop, DBLP, SemanticScholar, and GOOGLE Scholar Citations.


Conference and Event Organizations:

Co-Chair of the ICML 2018 Workshop Program

General Co-Chair of UAI 2018

Co-Organizer of the 14th biannual Conference of the German Society for Cognitive Science 2018

Co-Chair of the UAI 2017 Program Committee

Co-Chair of the KDD 2015 Best Paper Award Committee

Co-Chair of the ECML PKDD 2013 Program Committee

Co-Chair of ACAI 2018 Summer School on Statistical Relational AI as part of the Relational AI Days (RAID) 2018, PC Co-Chair of the 4th European Starting AI Researcher Symposium (STAIRS) 2012, PC Co-Chair of the AAAI Student Abstract and Poster Program 2012-14

PC Co-Chair of ICML 2018 Enabling Reproducibility in Machine Learning MLTrain@RML Workshop, KDML 2018, DeLBP 2018, NIPS 2017 Highlights Workshop, DS+J 2017, DeLBP 2017, SymInfOpt 2017, BeyondLabeler 2016, StarAI 2014, Buda 2014, SRL 2012, StarAI 2012, CoLISD 2012, CMPL 2011, MLG 2011, StarAI 2010, SRL 2009, MLG 2007, Dagstuhl Seminar 07161

Selected Program Committees/Reviewer:

NIPS 2018, ICDM 2018, DSAA 2018, CP 2018, MLG 2018, KI 2018, NAACL-HLT 2018, WWW 2018, IJCAI-ECAI 2018 (AC), KDD 2018 (SPC), ICRL 2018, SIGMOD 2018, AAAI 2018 (SPC, Senior Member Track), ECMLPKDD 2017 (Nectar, PhD), ICDM 2017, CEx 2017, ENIC 2017, GenPlan 2017, KDML 2017, NLP/Journalism 2017, ISWC 2017, SIGMOD 2017, MLG 2017, SUM 2017, IJCAI 2017 (SPC), AAAI 2017 (SPC), MLSA 2017, KI 2017, ACML 2016 (SPC), ICDM 2016, UAI 2016, ECCV 2016, ECML PKDD 2016 (AC), ECAI 2016, IJCAI 2016, ICML 2016, KDD 2016 (AC), AAAI 2016 (SPC), DS 2016, KI 2016, MOD 2016, ICDM 2015, NIPS 2015, ECML PKDD 2015 (GEB, AC), IJCAI 2015 (SPC), MPD 2015, SUM 2015, CVPR 2015, ICML 2015, CoDS 2015, AAAI 2015 (Main, AIW), AAAI 2014 (SPC, SM, SA) , ECML PKDD 2014 (GEB, AC), ICDM 2014 (AC), ECAI 2014 (AC), PODS 2014, KDD 2014 (PC and Best Paper Award Committee), UAI 2014, NIPS 2014, SDM 2014, ACML 2014 (AC and Best Paper Award Committee), CIKM 2014 (KM Track), ESWC 2014, ILP 2014, KR 2014, PGM 2014, DS 2014, CoDS 2014, DATA 2014, LTPM 2014, Know@LOD 2014, MUSE 2014, SenseML 2014, ICML 2010 (AC and Best Paper Award Committee)

German Science Foundation (DFG), European Commission, European Research Council (ERC), US National Science Foundation (NSF), German-Israeli Foundation for Scienti c Research and Development (GIF), Freie und Hansestadt Hamburg - BWFG, Swiss National Science Foundation, The Netherlands Organisation for Scientifi c Research, Research Foundation - Flanders (FWO), The Ministry of Science and Technology of Israel, Alexander von Humboldt-Stiftung, Carl-Zeiss-Stiftung, The Royal Society of New Zealand, German Academic Exchange Service (DAAD)

Editorial Boards:

Frontiers in Big Data - Machine Learning and Artificial Intelligence
Specialty Chief Editor (2018-)

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Action Editor (2017-)
Machine Learning Journal (MLJ)
Action Editor (2011-)
Data Mining and Knowledge Discovery (DAMI)
Action Editor (2011-)

Journal of Artificial Intelligence Research (JAIR)
Action Editor (2011-2017)
Artificial Intelligence Journal (AIJ)
Action Editor (2013-)
KI - Künstliche Intelligence
Editor (2017-)

New Computing Generation (EB, 2011-), Information (EB, 2016-), Big Data and Cognitive Computing (EB, 2016-)

Scientific Advisory Boards and Expert Groups

BMBF Platform Lernende Systeme, 2018-

Robert Bosch Centre for Data Science and Artificial Intelligence, IIT Madras, India, 2018-

Kompetenzzentrum Verbraucherforschung NRW, 2018-

BMBF Project ABIDA - Assessing Big Data, 2015-, 2015-2017, 2016, 2016-2017

GameAnalytics, 2012-2014

Invited Talks, Panels and Training

Talks and Panels

"Relational Quadratic Programming": 14th International Conference on Integration of Artificial Intelligence and Operations Research Techniques in Constraint Programming (CPAIOR 2017)
"Declarative Data Science Programming": 25th Annual Machine Learning Conference of Belgium and The Netherlands (BeneLearn 2016)

"Collective Attention on the Web": 19th International Conference on Discovery Science (DS 2016)
"Declarative Programming for Statistical ML": The 2016 Machine Learning Confrence (MLconf 2016 Seattle)

"Democratization of Optimization": 14th Conference of the Italian Association for Artificial Intelligence (AI*IA 2015)
"Collective Attention on the Web": Winter Conference on Network Science (NetSci-X 2016)

"Lifted Probabilistic Inference": Frontiers in AI Track of the 20th European Conference on Artificial Intelligence (ECAI 2012)
"Increasing Representational Power and Scaling Inference in Reinforcement Learning": 9th European Workshop on Reinforcement Learning (EWRL 2011)

"Probabilistic Logic Learning and Reasoning": 14th Annual Machine Learning Conference of Belgium and the Netherlands (BeneLearn 2005)

"The Automated Data Scientist": 2nd Jaenaer Data Science Day 2018"
"Tractable Data Journalism": SciCAR - Where Science Meets Computer Assisted Reporting 2017
"Journalist plus Wissenschaftler: Dreamteam für post fact checking": nr.Jahreskonferenz 2017

"Datensammeln: Messies oder der Sieg der Induktion?": Stadtgespräche im Musuem 2017

"Thinking Data Science Machines":
Distinguished Lecturer Series, Jena, 2017

"Modelling Traffic Counts":
GCRI, New York, 2016

"Populisten, Autokraten, Despoten-Wie wehrhaft ist unsere Demokratie?"

"Data Mining":

"Algorithmen-Wer kontrolliert die neuen Machthaber?": nr.Jahreskonferenz 2015

"Tractable Data Journalism": Berlin Machine Learning Meetup Group, October 2017
"Thinking Machine Learning": NIPS 2016 Workshop on Neurorobotics: A Chance for New Ideas, Algorithms and Approaches
"Daten! Sind sie Leben?" Kneipengespräch der "Lust an Wissenschaft?" 2016 Serie der Mercator Global Young Faculty
"Declarative Data Science Programming": Software Engineering and Machine Learning Workshop at the 10th Heinz Nixdorf Symposium 2016
"Lifted Machine Learning": International School on Human-Centred Computing (HCC 2016)
"Collective Attention on the Web": International School and Conference on Network Science (NetSci-X 2016)
"Democratization of Optimization" AAAI 2016 Workshop on Declarative Learning Based Programming (DeLBP 2016)
"Democratization of Optimization": 5th International Workshop on Statistical Relational AI (StarAI 2015)
"Democratization of Optimization": IJCAI 2015 Invited Sister Conference Presentations ML Track
"Poisson Dependency Networks": 2nd International Workshop on Mining Urban Data (MUD 2015)
"High Throughout Phenotyping: A Big Data Mining Challenge": 3rd Brazilian-German Frontiers of Science and Technology Symposium (BRAGFOST 2012)
"High Throughout Phenotyping: A Big Data Mining Challenge": Lernen, Wissen, Adaptivität (LWA 2012)
"From Lifted Probabilistic Inference to Lifted Linear Programming": 7th International Workshop on Uncertainty Reasoning for the Semantic Web (URSW 2011)
"Statistical Relational Artificial Intelligence": 5th Sino-German Frontiers of Science Symposium (SINOGFOS 2012)
"From Lifted Probabilistic Inference to Lifted Linear Programming": 7th International Workshop on Uncertainty Reasoning for the Semantic Web (URSW 2012)
"Perception and Prediction Beyond the Here and Now": 2nd International Workshop on Mining Ubiquitous and Social Environments (MUSE 2011)
"Lifted Message Passing": 6th International Workshop onNeural-Symbolic Learning and Reasoning (NeSys 2010)
"Lifted Message Passing": International Workshop on Graphical Models in Robotics (GraphBot 2010)
"Relations and Probabilities: Friends, not Foes": Lernen, Wissen, Adaptivität (LWA 2009)
"Probabilistic Logic Learning and Reasoning": 14th Annual Machine Learning Conference of Belgium and the Netherlands (BeneLearn 2005)

Tutorials, Seminars and Training

"Statistical Relational Artificial Intelligence: Logic, Probability, and Computation", NIPS 2017

"Feeding the World with Big Data", Computational Sustainability Virtual Seminar Series, Cornell University, USA, fall 2017

"Tractable Probabilistic Graphical Models", 4th International Summer School on Resource-aware Machine Learning 2017
"Artificial Intelligence - Facts, Chances, Risks", Research Training Group of the German National Academic Scholarship Foundation 2017-18
"Statistical Relational Artificial Intelligence: Logic, Probability, and Computation", AAAI 2017
"Data-Diven Plant Phenotyping", PHENOMICS Workshop Berlin 2016
"Statistical Relational Artificial Intelligence: Logic, Probability, and Computation", HCC 2016
"60 Years of Artificial Intelligence - Where are we?", Summer Academy of the German National Academic Scholarship Foundation 2015
"Statistical (Relational) Learning and Lifted inference", MLSMA 2014
"Lifted Approximate Inference: Methods and Theory", AAAI 2014
"Combining Logic and Probability: Languages, Algorithms, and Applications", AAAI 2013
"Lifted Inference in Probabilistic Logical Models", IJCAI 2011
"Statistical Relational Learning", MLSS 2010
"First-order Planning", ICAPS 2008
"SRL without Tears: An ILP Perspective on SRL", ILP 2008
"Decision-Theoretic Planning and Learning in Relational Domains", AAAI 2008
"Probabilistic Inductive Logic Learning", ECMLPKDD 2005
"Probabilistic Inductive Logic Learning", IDA 2005
"Probabilistic Logic Learning", ICML 2004

Group Members and Alumni

Elena Erdmann
Alejandro Molina
Patrick Schramowski
Karl Stelzner
Fabrizio Ventola
Babak Ahmadi (PhD)
Fabian Hadiji (PhD)
Ahmed Jawad (PhD)
Marion Neumann (PhD)
Washington University, St. Louis
Mirwaes Wahabzada (PhD)
University of Bonn
Martin Mladenov
Google Research
Zhao Xu (PostDoc)


"Was ist eigentlich Künstliche Intelligenz?", Children's university lecture, comprehensive school Gänsewinkel Schwerte, Germany, fall 2017

Probabilistische Graphische Modelle, ACATECH Massiv Open Online Course on "Machine Learning", spring 2017

Extended Seminar on "Interactive Machine Learning." winter 2017
Course on "Statistical Relational Artificial Intelligence." winter 2017
Course on "Probabilistic Graphical Models." winter 2017
Project group on Manipulation "Entwicklung und kritische Beleuchtung eines Frameworks zur Extraktion und Übertragung semantischer Informationen zwischen Videos." summer-winter 2017
Ph.D. course on Statistical Relational AI at the Università degli Studi di Trento. spring 2017
Ph.D. course on Lifted Inference and Collective Attention at the Università di Bari. summer 2016
Course on Wissensentdeckung in Datenbanken. summer 2014, 2016
Course on Statistical Relational Learning together with F. Riguzzi (U. Ferrara, Italy) as part of ERASMUS+. summer 2016
Course on Foundations of Data Science. summer 2015, winter 15, 2016
Course on Mathematik fuer Informatiker 1. summer 2015
Course on Probabilistic Graphical Models. winter 2013, 2014, 2015, 2016
Proseminar on Big Data Mining. summer 2014, 2015
Project group on DeepNewsDive: Maschinen lesen Zeitungen. summer-winter 2016
Project group on Infoscreens. summer-winter 2015
Seminar on Big Data Mining. winter 2013
Co-organized a project on Across Scale Data Analysis. summer 2013
Course on Probabilistic Graphical Models. winter 2012
Co-organized course on Geoalgorithms and geo data structurs. winter 2012
Organized project lab on Data Mining and Pattern Recognition. winter 2012
Seminar on Geoinformation III. winter 2012
Course on Probabilistic Graphical Models. winter 2012
Course on Probabilistic Graphical Models. winter 2011
Co-organized practical lab with topics on Lifted Inference and IR. winter 2010
Course on Probabilistic Graphical Models. summer 2009, 2010
Co-organized seminar on Machine Learning for Computer Games. winter 2008
Course on Bayesian networks as part of the Advanced AI course. winter 2006


Argumentative Machine Learning (KE 1686/3-1, SPP 1999, DFG)
In this DFG project, we will investigate radically novel machine learning approaches in detail and develop the new field of “argumentative machine learning” in general: a tight integration of Computational Argumentation and Machine Learning. This has several benefits. The use of argumentation techniques allows to obtain classifiers, which are by design able to explain their decisions, and therefore addresses the recent need for Explainable AI : classifications are accompanied by a dialectical analysis showing why arguments for the conclusion are preferred to counterarguments; this automatic deliberation, validation, reconstruction and synthesis of arguments helps in assessing trust in the classifier, which is fundamental if one plans to take action based on a prediction. Argumentation techniques in machine learning also allows the easy integration of additional expert knowledge in form of arguments.
Connecting Editors and Researchers (Zeit Online, GRK 1994, DFG)
Data Journalism, News Recommendation, and Fake News Detection: more and more AI techniques find there way into (on-line) journalism application. However, the use of Data Science, Natural Language Processing and Machine Learning in Journalism is still at the beginning. So far, there is a significant discrepancy between research and Editor's everyday life. In this cooperation between Zeit Online and the TU Darmstadt as well as the DFG Research Training Group GRK 1994 "Adaptive Preparation of Information from Heterogeneous Sources" (AIPHES), we aim at closing this gap and build a bridge between the disciplines.
Deep Inference Machines (GRK 1994, DFG)
Inference machines, viewing inference computations as trainable computation graphs, have paved the way to “deepify” classical language models. Viewing paraphrasing and harmonization as an inference task in data-driven relational probabilistic models, we therefore recast relational inference using inference machines in this project within the DFG Research Training Group GRK 1994 "Adaptive Preparation of Information from Heterogeneous Sources" (AIPHES. This allows us to lift recent advances in deep (language) modeling and learning to relational domains, consisting of (textual and visual) objects and relations among them, and to explore the resulting deep relational inference machines for data-driven textual and visual inference over heterogeneous domains.
Deep Phenotyping (BLE)
The goal of this BLE project is the optimization and objectification of phenotyping routines for crop breeding. It combines sensor technology, automation and deep learning. By using hyperspectral images and deep learning it will help to go beyond a purely visually assessed disease score for phenotyping of different genotypes., EXIST
The start-up is providing an innovative machine learning technology to maximize engagement and retention for mobile apps, e-commerce, or SaaS products. It is supported by EXIST, a support programme of the German Federal Ministry for Economic Affairs and Energy (BMWi). This programme aims at improving the entrepreneurial environment at universities and research institutes. It also aims at increasing the number and success of technology and knowledge based business start-ups.
Resource-efficient Graph Mining (SFB 876,DFG)
Linked data and networks occur often in the context of embedded systems. Sensors, RFID-chips, cameras, etc. of products of our daily life continuously produce data and communicate with each other as well as the user. A natural representation of linked data are graphs where objects correspond to the vertices of the graph and the links to its edges. In this project, we will develop new approaches and algorithms for the classification of graphs and linked data sets under resource constraints. To this aim, randomized approaches from algorithmic theory, approaches for mining and learning with graphs (in particular graph kernels) and algorithmic engineering approaches have been combined in this SFB876 research project.
Analysis and Communication for Dynamic Traffic Prognosis (SFB 876, DFG)
The goal os this SFB876 research project is the development of high precision prediction methods for the dynamic behavior of road traffic based on resource-efficient transmission of extended Floating Car Data (xFCD) and other data sources. With the help of collected data from vehicles, triggers for disturbances of the traffic flow should be detected early and countermeasures are applied in real-time. New dynamic microscopic traffic models are needed. Applying Data Mining strategies, these models are re-parameterized in real time in order to handle the heterogeneity of urban traffic.
Efficient Inference for Probabilistic Relational Models using Symmetries and Linear Programming Relaxations (GIF)
Say we know that some people in a social network are friends and some are smokers, how can we infer whether others are smokers and friends? For thousands of people this seems like a daunting computational task. However, such tasks often have strong symmetries (i.e.,repeated structures) that should intuitively translate into fewer computations. In this project, we proposed a novel approach to designing “symmetry aware” algorithms. We built on linear programming (LP) relaxations as the key underlying framework. Despite the popularity of LP relaxations in the graphical models community, they have seen very little use within the SRL literature. In this GIF project, we developed the theory and algorithms needed for applying LPs to SRL, while making effective use of symmetries.
Flexible Skill Acquisition and Intuitive Robot Tasking for Mobile Manipulation in the Real World (EU)
Flexible Skill Acquisition and Intuitive Robot Tasking for Mobile Manipulation in the Real World was a project funded by the European Commission within FP7. The goal of First-MM is to build the basis for a new generation of autonomous mobile manipulation robots that can flexibly be instructed to perform complex manipulation and transportation tasks. The project has focussed on developing a novel robot programming environment that allows even non-expert users to specify complex manipulation tasks in real-world environments. To this aim, we have built upon and extend results in robot programming, navigation, manipulation, perception, learning by instruction, and statistical relational learning to develop advanced technology for mobile manipulation robots that can flexibly be instructed even by non-expert users to perform challenging manipulation tasks in real-world environments.
Relational exploration, learning and inference (SPP 1527, DFG)
The core approach of this DFG project is to organize exploration, learning and inference on appropriate relational representations implying strong prior assumptions on the world structure. On these representations we can learn from uncertain experience compact models of action effects that generalize across objects. We transfer existing exploration theories to relational representations—leading to a novel level of explorative behavior that decidedly aims to explore objects to which the current knowledge does not generalize. This project was to our knowledge the first to combine statistical relational learning methods to tackle core problems in intelligent robotics, fueling the hope for a major advance in the field. We have demonstrated our methods on real-world robot platforms manipulating their environments.
The ability to build computing systems that can observe, understand and act on human activity has long been a goal of computing research. Such systems could have profound conceptual and practical implications. Since the ability to reason and act based on activity is one of the central aspects of human intelligence, from a conceptual viewpoint such a system could cast light on computational models of intelligence. More tangibly, perhaps, machines that reason about human activity could aid humans in aspects of their lives that are today considered outside the domain of machines.
Most existing activity mining approaches indeed take uncertainties into account, but they do not consider the rich relations among people and objects that exist in the real world. STREAM’s goal was to develop formalisms, models, and algorithms for effective and robust statistical relational activity mining that enables one to develop socio-cognitive aware systems and to apply them on significant real-life applications. To this aim STREAM develop statistical relational learning methods using a Fraunhofer ATTRACT fellowship.
One of the key open questions of artificial intelligence concerns "probabilistic logic learning", i.e.the integration of probabilistic reasoning, with first order logic representations and machine learning. The overall goal of the APrIL II project is therefore to develop a sound theoretical understanding of "probabilistic logic learning" that enables one to develop effective probabilistic logic learning systems and to apply them on significant real-life applications. To realize this aim, the APrIL II consortium will (1) develop a number of significant "show-case" applications of "probabilistic logic learning" in the area of bio-informatics, more specifically, concerning protein folding, metabolic pathways, and genetics.(2) develop the needed theory, probabilistic representations, learning algorithms and systems for learning interesting probabilistic logic models in real-life applications on the basis of data. The methodology applied is that of the field of inductive logic programming, which explains the title of the project.