thon.bib
@inproceedings{thon09icaps_pl,
title = {From non-deterministic to probabilistic planning with the help of statistical relational learning},
author = {Ingo Thon and Bernd Gutmann and Martijn van Otterlo and Niels Landwehr and Luc De Raedt},
booktilte = {ICAPS 2009 - Proceedings of the Workshop on Planning and Learning},
year = {2009},
month = {September},
abstract = {Using machine learning techniques for planning is getting increasingly more important in recent years. Various aspects of action models can be induced from data and then exploited for planning. For probabilistic planning, natural candidates are learning of action effects and their probabilities. For expressive formalisms such as PPDDL, this is a difficult prob- lem since they can introduce easily a hidden data problem; the fact that multiple action outcomes may have generated the same experienced state transitions in the data. Furthermore the action effects might be factored such that this prob- lem requires solving a constraint satisfaction problem within an expectation maximization scheme. In this paper we outline how to utilize recent techniques from the field of statistical relational learning for this problem. More specifically, we show how techniques developed for the CPT-L model of relational probabilistic sequences can be applied to the problem of learning probabilities in a PPDDL model. A CPT-L model concisely specify a Markov chain over arbitrary numbers of objects in the domain and simultaneous applications of multiple actions. The use of efficient BDD-style representations allows for fast and efficient learning in such domains. Even efficient online learning is possible as we will show in this paper. We relate to other learning approaches for similar domains and highlight the opportunities for incorporating our approach into architectures that can plan, execute the plan, and learn from the outcomes, in an online and incremental fashion.
}
}
@inproceedings{thon09ilp,
title = {Don't Fear Optimality: Sampling for Probabilistic-Logic Sequence Models (Extended Abstract)},
author = {Ingo Thon},
booktitle = {Preliminary Proceedings of the International Conference on Inductive Logic Programming (ILP-2009)},
year = {2009},
month = {July},
abstract = {One of the current challenges in artificial intelligence is modeling dynamic environments
that change due to the actions or activities undertaken by people or agents.
The task of inferring hidden states, e.g. the activities or intentions of people, based on
observations is called filtering. Standard probabilistic models such as Dynamic Bayesian
Networks are able to solve this task efficiently using approximative methods such as particle
filters. However, these models do not support logical or relational representations.
The key contribution of this paper is the upgrade of a particle filter algorithm for use
with a probabilistic logical representation through the definition of a proposal distribution.
The performance of the algorithm depends largely on how well this
distribution fits the target distribution.
We adopt the idea of logical compilation into Binary Decision
Diagrams for sampling. This allows us to use the optimal proposal distribution which is
normally prohibitively slow.
},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/237392/1/thon09ilp2.pdf}
}
@inproceedings{antanas09ilp,
author = {Laura-Andreea Antanas and Ingo Thon and Martijn van Otterlo and Niels Landwehr and Luc De Raedt},
title = {Probabilistic logical sequence learning for video},
booktitle = {Preliminary Proceedings of the International Conference on Inductive Logic Programming (ILP-2009)},
year = {2009},
month = {July},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/233212/1/ilp_new.pdf},
abstract = {Understanding complex, dynamic scenes of real-world activities from low-level
sensor data is of central importance for intelligent systems. The main difficulty
lies in the fact that complex scenes are best described in high-level, logical
formalisms, while sensor data usually consists of many low-level features. We
first propose a method to obtain a logical representation of real-world, dynamic
scenes based on input video stream solely. We focus on representing the video
data using probabilistic relational sequences as a natural way to incorporate
sensor uncertainty. They allow us to work with structured terms, and in addition
they capture the inherent uncertainty of object detection. Further on, we employ
r-grams as the probabilistic logical learning model for this application. In a
first step we use r-grams in a simple setting and we show their viability in card
games. We also show how r-grams can be upgraded to deal with uncertain observations.}
}
@inproceedings{bruynooghe:srl09,
author = {Maurice Bruynooghe and Broes {De Cat} and Jochen
Drijkoningen and Daan Fierens and Jan Goos and Bernd
Gutmann and Angelika Kimmig and Wouter Labeeuw and
Steven Langenaken and Niels Landwehr and Wannes
Meert and Ewoud Nuyts and Robin Pellegrims and Roel
Rymenants and Stefan Segers and Ingo Thon and Jelle
{Van Eyck} and Guy {Van den Broeck} and Tine
Vangansewinkel and Lucie {Van Hove} and Joost
Vennekens and Timmy Weytjens and Luc {De Raedt}},
title = {An Exercise with Statistical Relational Learning
Systems},
booktitle = {International Workshop on Statistical Relational
Learning (SRL-2009)},
year = 2009,
editor = {Pedro Domingos and Kristian Kersting},
address = {Leuven, Belgium},
month = {July},
abstract = {We report on two exercises in modeling, in
ference and learning with seven statistical
relational learning systems and use this as
a basis for a simple and preliminary comparison
between these systems},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/230569/1/srl09_capita.pdf}
}
@inproceedings{antanas09benelearn,
title = {Learning probabilistic relational models from sequential video data with applications in
table-top and card games},
author = {Laura-Andreea Antanas and Martijn van Otterlo and Luc De Raedt and Ingo Thon},
booktitle = {Benelearn edition:18 location:Tilburg date:18-19 May 2009},
year = {2009},
month = {June},
abstract = {Being able to understand complex dynamic scenes of real-world activities from
low-level sensor data is of central importance for intelligent systems. The main
difficulty lies in the fact that complex scenes are best described in high-level,
logical formalisms, whereas sensor data usually consists of many low-level feature
values. In this work, we consider the problem of learning high-level, logical
descriptions of dynamic scenes based on input video stream solely. In order to
learn such general patterns, two important problems must be tackled and their
solutions combined: obtaining high-level, logical representations from video
data and learning probabilistic logical models of dynamic scenes. This setting
opens new research directions. We focus on representing the video data using
probabilistic relational sequences as a natural way to incorporate sensor information
in real-world tasks. They allow to work with structured terms, but in addition they
capture the inherent uncertainty of object detection. Further on, we employ relational
sequence learning methods for this type of video representation. We propose table-top
and card games as application domain.},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/228573/1/ben2009_CardGames.pdf}
}
@inproceedings{raedt-ppulsa08,
author = {Luc {De Raedt} and Bart Demoen and Daan Fierens and
Bernd Gutmann and Gerda Janssens and Angelika Kimmig
and Niels Landwehr and Theofrastos Mantadelis and
Wannes Meert and Ricardo Rocha and V{\`i}tor
{Santos~Costa} and Ingo Thon and Joost Vennekens},
title = {Towards Digesting the Alphabet-Soup of Statistical
Relational Learning},
booktitle = {Proceedings of the 1st Workshop on Probabilistic
Programming: Universal Languages, Systems and
Applications},
editor = {Daniel Roy and John Winn and David McAllester and
Vikash Mansinghka and Joshua Tenenbaum},
month = {December},
year = 2008,
address = {Whistler, Canada},
abstract = {This paper reports on our work towards the development of a probabilistic logic
programming environment intended as a target language in which other probabilistic
languages can be compiled, thereby contributing to the digestion of the
"alphabet soup". },
pdf = {https://lirias.kuleuven.be/bitstream/123456789/206421/1/nips_pll.pdf}
}
@article{landwehr:fi08,
author = {Niels Landwehr and Bernd Gutmann and Ingo Thon and
Luc {De Raedt} and Matthai Philipose},
title = {Relational Transformation-based Tagging for Activity
Recognition},
journal = {Fundamenta Informaticae},
year = 2008,
volume = 89,
number = 1,
pages = {111--129},
web = {http://iospress.metapress.com/content/u040211744m2w8v2/},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/207360/6/landwehrFI08.pdf},
abstract = {The ability to recognize human activities from sensory information is essential for
developing the next generation of smart devices. Many human activity recognition
tasks are - from a machine learning perspective - quite similar to tagging tasks
in natural language processing. Motivated by this similarity, we develop a relational
transformation-based tagging system based on inductive logic programming principles,
which is able to cope with expressive relational representations as well as a
background theory. The approach is experimentally evaluated on two activity
recognition tasks and an information extraction task, and compared to Hidden Markov
Models, one of the most popular and successful approaches for tagging.
}
}
@inproceedings{thon08ilp,
title = {A Simple Model for Sequences of Relational State Descriptions},
author = {Ingo Thon and Niels Landwehr and Luc De Raedt},
year = 2008,
month = sep,
booktitle = {Inductive Logic Programming, Late Breaking Papers pages:111-116},
abstract = {Artificial intelligence aims at developing agents that learn and act in
complex environments. Realistic environments typically feature a variable number
of objects, relations amongst them, and non-deterministic transition behavior.
Standard probabilistic sequence models provide efficient inference and learning
techniques, but typically cannot fully capture the relational complexity. On the
other hand, statistical relational learning techniques are often too inefficient. In
this paper, we present a simple model that occupies an intermediate position in
this expressiveness/efficiency trade-off. Based on CP-logic, an expressive probabilistic
logic for modeling causality. but specialized to represent a probability
distribution over sequences of relational state descriptions, and employing a Markov
assumption, inference and learning become more tractable and effective.},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/202008/1/thon08ilplate.pdf}
}
@inproceedings{DBLP:conf/pkdd/ThonLR08,
author = {Ingo Thon and
Niels Landwehr and
Luc De Raedt},
title = {{A Simple Model for Sequences of Relational State Descriptions}},
booktitle = {Proceedings of the 19th European Conference on Machine Learning},
year = {2008},
month = sep,
pages = {506-521},
optee = {http://dx.doi.org/10.1007/978-3-540-87481-2_33},
optcrossref = {DBLP:conf/pkdd/2008-2},
optbibsource = {DBLP, http://dblp.uni-trier.de},
abstract = {Artificial intelligence aims at developing agents that learn and act in
complex environments. Realistic environments typically feature a variable
number of objects, relations amongst them, and non-deterministic transition
behavior.
Standard probabilistic sequence models provide efficient inference and
learning techniques, but typically cannot fully capture the relational
complexity. On the other hand, statistical relational learning techniques
are often too inefficient. In this paper, we present a simple model that
occupies an intermediate position in this expressiveness/efficiency trade-off.
It is based on CP-logic, an expressive probabilistic logic for modeling
causality. However, by specializing CP-logic to represent a probability
distribution over sequences of relational state descriptions, and employing
a Markov assumption, inference and learning become more tractable and effective.
We show that the resulting model is able to handle probabilistic relational
domains with a substantial number of objects and relations.},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/199222/4/thon08ecml.pdf},
video = {http://videolectures.net/ecmlpkdd08_thon_asmf/}
}
@inproceedings{thon08mlg,
author = {Ingo Thon and Niels Landwehr and Luc De Raedt},
title = {CPT-L: An efficient model for relational stochastic processes},
year = {2008},
month = {July},
booktitle = {International Workshop on Mining and Learning with Graphs (MLG 2008) edition:6 location:Helsinki,
Finland date:4-5 July 2008},
abstract = {Agents that learn and act in real-world environments have to cope with
both complex state descriptions and non-deterministic transition
behavior of the world. Standard statistical relational learning
techniques can capture this complexity, but are often inefficient.
We present a simple probabilistic model for such environments based
on CP-Logic. Efficiency is maintained by restriction to a fully
observable setting and the use of efficient inference algorithms
based on binary decision diagrams.},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/203697/1/thon08mlg.pdf}
}
@inproceedings{thon08benelearn,
author = {Ingo Thon and Niels Landwehr and Luc De Raedt},
title = {CPT-L: An efficient model for relational stochastic processes},
booktitle = {Benelearn 08},
year = 2008,
address = {Spa, Belgium},
month = {May},
editor = {Louis Wehenkel and Pierre Geurts and Raphae{\"e}l
Mar{\'e}e},
pages = {27--28},
abstract = {Agents that learn and act in real-world environments have to cope with both complex state
descriptions and non-deterministic transition behavior of the world.
Standard statistical relational learning techniques can capture this
complexity, but are often inefficient. We present a simple probabilistic
model for such environments based on CP-Logic. efficiency is maintained
by restriction to a fully observable setting.},
pdf = {https://lirias.kuleuven.be/bitstream/123456789/203702/1/thon08benelearn.pdf}
}
@inproceedings{landwehr:iwkdus07,
author = {Niels Landwehr and Bernd Gutmann and Ingo Thon and
Matthai Philipose and Luc {De~Raedt}},
title = {Relational Transformation-based Tagging for Human
Activity Recognition},
booktitle = {Proceedings of the International Workshop on
Knowledge Discovery from Ubiquitious Data Streams
(IWKDUS07)},
pages = {83--94},
year = 2007,
editor = {Jo{\~ao} Gama and Mohamed Medhat Gaber and Jes{\'u}s
Aguilar-Ruiz},
address = {Warsaw, Poland},
month = {September}
}
@inproceedings{landwehr:mrdm07,
author = {Niels Landwehr and Bernd Gutmann and Ingo Thon and
Matthai Philipose and Luc {De~Raedt}},
title = {Relational Transformation-based Tagging for Human
Activity Recognition},
booktitle = {Proceedings of the 6th International Workshop on
Multi-relational Data Mining (MRDM07)},
pages = {81--92},
year = 2007,
editor = {Donato Malerba and Annalisa Appice and Michelangelo
Ceci},
address = {Warsaw, Poland},
month = {September}
}
@inproceedings{thon:mrdm07,
author = {Ingo Thon and Kristian Kersting},
title = {Distributed relational state representations for complex stochastic processes},
booktitle = {Proceedings of the 6th International Workshop on
Multi-relational Data Mining (MRDM07)},
pages = {129--140},
year = 2007,
editor = {Donato Malerba and Annalisa Appice and Michelangelo Ceci},
address = {Warsaw, Poland},
month = {September},
abstract = {Several promising variants of hidden Markov models (HMMs)
have recently been developed to efficiently deal with large state and
observation spaces and relational structure. Many application domains,
however, have an apriori componential structure such as parts in musical
scores. In this case, exact inference within relational HMMs still
grows exponentially in the number of components. In this paper, we propose
to approximate the complex joint relational HMM with a simpler,
distributed one: k relational hidden chains over n states, one for each
component. Then, we iteratively perform inference for each chain given
fixed values for the other chains until convergence. Due to this structured
mean field approximation, the effective size of the hidden state
space collapses from O(n to the power of k ) to O(k * n). }
}
@inproceedings{thon:mlg07,
author = {Ingo Thon and Kristian Kersting},
title = {Distributed relational state representations for complex stochastic processes},
booktitle = {Proceedings of the 5th International Workshop on
Mining and Learning with Graphs (MLG 2007)},
year = 2007,
editor = {Paolo Frasconi and Kristian Kersting and Koji Tsuda},
address = {Florence, Italy},
month = {August},
note = {Extended Abstract}
}
This file was generated by bibtex2html 1.94.