33 Search Results for "De Raedt, Luc"


Document
Learning MAX-SAT Models from Examples Using Genetic Algorithms and Knowledge Compilation

Authors: Senne Berden, Mohit Kumar, Samuel Kolb, and Tias Guns

Published in: LIPIcs, Volume 235, 28th International Conference on Principles and Practice of Constraint Programming (CP 2022)


Abstract
Many real-world problems can be effectively solved by means of combinatorial optimization. However, appropriate models to give to a solver are not always available, and sometimes must be learned from historical data. Although some research has been done in this area, the task of learning (weighted partial) MAX-SAT models has not received much attention thus far, even though such models can be used in many real-world applications. Furthermore, most existing work is limited to learning models from non-contextual data, where instances are labeled as solutions and non-solutions, but without any specification of the contexts in which those labels apply. A recent approach named hassle-sls has addressed these limitations: it can jointly learn hard constraints and weighted soft constraints from labeled contextual examples. However, it is hindered by long runtimes, as evaluating even a single candidate MAX-SAT model requires solving as many models as there are contexts in the training data, which quickly becomes highly expensive when the size of the model increases. In this work, we address these runtime issues. To this end, we make two contributions. First, we propose a faster model evaluation procedure that makes use of knowledge compilation. Second, we propose a genetic algorithm named hassle-gen that decreases the number of evaluations needed to find good models. We experimentally show that both contributions improve on the state of the art by speeding up learning, which in turn allows higher-quality MAX-SAT models to be found within a given learning time budget.

Cite as

Senne Berden, Mohit Kumar, Samuel Kolb, and Tias Guns. Learning MAX-SAT Models from Examples Using Genetic Algorithms and Knowledge Compilation. In 28th International Conference on Principles and Practice of Constraint Programming (CP 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 235, pp. 8:1-8:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)


Copy BibTex To Clipboard

@InProceedings{berden_et_al:LIPIcs.CP.2022.8,
  author =	{Berden, Senne and Kumar, Mohit and Kolb, Samuel and Guns, Tias},
  title =	{{Learning MAX-SAT Models from Examples Using Genetic Algorithms and Knowledge Compilation}},
  booktitle =	{28th International Conference on Principles and Practice of Constraint Programming (CP 2022)},
  pages =	{8:1--8:17},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-240-2},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{235},
  editor =	{Solnon, Christine},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2022.8},
  URN =		{urn:nbn:de:0030-drops-166373},
  doi =		{10.4230/LIPIcs.CP.2022.8},
  annote =	{Keywords: Machine learning, constraint learning, MAX-SAT}
}
Document
Approaches and Applications of Inductive Programming (Dagstuhl Seminar 21192)

Authors: Andrew Cropper, Luc De Raedt, Richard Evans, and Ute Schmid

Published in: Dagstuhl Reports, Volume 11, Issue 4 (2021)


Abstract
In this report the program and the outcomes of Dagstuhl Seminar 21192 "Approaches and Applications of Inductive Programming" is documented. The goal of inductive programming (IP) is to induce computer programs from data, typically input/output examples of a desired program. IP interests researchers from many areas of computer science, including machine learning, automated reasoning, program verification, and software engineering. Furthermore, IP contributes to research outside computer science, notably in cognitive science, where IP can help build models of human inductive learning and contribute methods for intelligent tutor systems. Building on the success of previous IP Dagstuhl seminars (13502, 15442, 17382, and 19202), the goal of this new edition of the seminar is to focus on IP methods which integrate learning and reasoning, scaling up IP methods to be applicable to more complex real world problems, and to further explore the potential of IP for explainable artificial intelligence (XAI), especially for interactive learning. The extended abstracts included in this report show recent advances in IP research. The included short report of the outcome of the discussion sessions additionally point out interesting interrelation between different aspects and possible new directions for IP.

Cite as

Andrew Cropper, Luc De Raedt, Richard Evans, and Ute Schmid. Approaches and Applications of Inductive Programming (Dagstuhl Seminar 21192). In Dagstuhl Reports, Volume 11, Issue 4, pp. 20-33, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2021)


Copy BibTex To Clipboard

@Article{cropper_et_al:DagRep.11.4.20,
  author =	{Cropper, Andrew and De Raedt, Luc and Evans, Richard and Schmid, Ute},
  title =	{{Approaches and Applications of Inductive Programming (Dagstuhl Seminar 21192)}},
  pages =	{20--33},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2021},
  volume =	{11},
  number =	{4},
  editor =	{Cropper, Andrew and De Raedt, Luc and Evans, Richard and Schmid, Ute},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagRep.11.4.20},
  URN =		{urn:nbn:de:0030-drops-147975},
  doi =		{10.4230/DagRep.11.4.20},
  annote =	{Keywords: Interpretable Machine Learning, Explainable Artificial Intelligence, Interactive Learning, Human-like Computing, Inductive Logic Programming}
}
Document
Approaches and Applications of Inductive Programming (Dagstuhl Seminar 19202)

Authors: Luc De Raedt, Richard Evans, Stephen H. Muggleton, and Ute Schmid

Published in: Dagstuhl Reports, Volume 9, Issue 5 (2019)


Abstract
In this report the program and the outcomes of Dagstuhl Seminar 19202 "Approaches and Applications of Inductive Programming" is documented. After a short introduction to the state of the art to inductive programming research, an overview of the introductory tutorials, the talks, program demonstrations, and the outcomes of discussion groups is given.

Cite as

Luc De Raedt, Richard Evans, Stephen H. Muggleton, and Ute Schmid. Approaches and Applications of Inductive Programming (Dagstuhl Seminar 19202). In Dagstuhl Reports, Volume 9, Issue 5, pp. 58-88, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@Article{deraedt_et_al:DagRep.9.5.58,
  author =	{De Raedt, Luc and Evans, Richard and Muggleton, Stephen H. and Schmid, Ute},
  title =	{{Approaches and Applications of Inductive Programming (Dagstuhl Seminar 19202)}},
  pages =	{58--88},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2019},
  volume =	{9},
  number =	{5},
  editor =	{De Raedt, Luc and Evans, Richard and Muggleton, Stephen H. and Schmid, Ute},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagRep.9.5.58},
  URN =		{urn:nbn:de:0030-drops-113810},
  doi =		{10.4230/DagRep.9.5.58},
  annote =	{Keywords: Enduser programming, Explainable AI, Human-like computing, Inductive logic programming, Probabilistic programming}
}
Document
Automating Data Science (Dagstuhl Seminar 18401)

Authors: Tijl De Bie, Luc De Raedt, Holger H. Hoos, and Padhraic Smyth

Published in: Dagstuhl Reports, Volume 8, Issue 9 (2019)


Abstract
Data science is concerned with the extraction of knowledge and insight, and ultimately societal or economic value, from data. It complements traditional statistics in that its object is data as it presents itself in the wild (often complex and heterogeneous, noisy, loosely structured, biased, etc.), rather than well-structured data sampled in carefully designed studies. It also has a strong computer science focus, and is related to popular areas such as big data, machine learning, data mining and knowledge discovery. Data science is becoming increasingly important with the abundance of big data, while the number of skilled data scientists is lagging. This has raised the question as to whether it is possible to automate data science in several contexts. First, from an artificial intelligence perspective, it is interesting to investigate whether (data) science (or portions of it) can be automated, as it is an activity currently requiring high levels of human expertise. Second, the field of machine learning has a long-standing interest in applying machine learning at the meta-level, in order to obtain better machine learning algorithms, yielding recent successes in automated parameter tuning, algorithm configuration and algorithm selection. Third, there is an interest in automating not only the model building process itself (cf. the Automated Statistician) but also in automating the preprocessing steps (data wrangling). This Dagstuhl seminar brought together researchers from all areas concerned with data science in order to study whether, to what extent, and how data science can be automated.

Cite as

Tijl De Bie, Luc De Raedt, Holger H. Hoos, and Padhraic Smyth. Automating Data Science (Dagstuhl Seminar 18401). In Dagstuhl Reports, Volume 8, Issue 9, pp. 154-181, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@Article{debie_et_al:DagRep.8.9.154,
  author =	{De Bie, Tijl and De Raedt, Luc and Hoos, Holger H. and Smyth, Padhraic},
  title =	{{Automating Data Science  (Dagstuhl Seminar 18401)}},
  pages =	{154--181},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2019},
  volume =	{8},
  number =	{9},
  editor =	{De Bie, Tijl and De Raedt, Luc and Hoos, Holger H. and Smyth, Padhraic},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagRep.8.9.154},
  URN =		{urn:nbn:de:0030-drops-103443},
  doi =		{10.4230/DagRep.8.9.154},
  annote =	{Keywords: artificial intelligence, automated machine learning, automated scientific discovery, data science, inductive programming}
}
Document
Constraints, Optimization and Data (Dagstuhl Seminar 14411)

Authors: Luc De Raedt, Siegfried Nijssen, Barry O'Sullivan, and Michele Sebag

Published in: Dagstuhl Reports, Volume 4, Issue 10 (2015)


Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 14411 "Constraints, Optimization and Data". Constraint programming and optimization have recently received considerable attention from the fields of machine learning and data mining; similarly, machine learning and data mining have received considerable attention from the fields of constraint programming and optimization. The goal of the seminar was to showcase recent progress in these different areas, with the objective of working towards a common basis of understanding, which should help to facilitate future synergies.

Cite as

Luc De Raedt, Siegfried Nijssen, Barry O'Sullivan, and Michele Sebag. Constraints, Optimization and Data (Dagstuhl Seminar 14411). In Dagstuhl Reports, Volume 4, Issue 10, pp. 1-31, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2015)


Copy BibTex To Clipboard

@Article{deraedt_et_al:DagRep.4.10.1,
  author =	{De Raedt, Luc and Nijssen, Siegfried and O'Sullivan, Barry and Sebag, Michele},
  title =	{{Constraints, Optimization and Data (Dagstuhl Seminar 14411)}},
  pages =	{1--31},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2015},
  volume =	{4},
  number =	{10},
  editor =	{De Raedt, Luc and Nijssen, Siegfried and O'Sullivan, Barry and Sebag, Michele},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagRep.4.10.1},
  URN =		{urn:nbn:de:0030-drops-48901},
  doi =		{10.4230/DagRep.4.10.1},
  annote =	{Keywords: Data mining, constraint programming, machine learning}
}
Document
Constraint Programming meets Machine Learning and Data Mining (Dagstuhl Seminar 11201)

Authors: Luc De Raedt, Siegfried Nijssen, Barry O'Sullivan, and Pascal Van Hentenryck

Published in: Dagstuhl Reports, Volume 1, Issue 5 (2011)


Abstract
This report documents the programme and the outcomes of Dagstuhl Seminar 11201 "Constraint Programming meets Machine Learning and Data Mining". Our starting point in this seminar was that machine learning and data mining have developed largely independently from constraint programming till now, but that it is increasingly becoming clear that there are many opportunities for interactions between these areas: on the one hand, data mining and machine learning can be used to improve constraint solving; on the other hand, constraint solving can be used in data mining in machine learning. This seminar brought together prominent researchers from both communities to discuss these opportunities.

Cite as

Luc De Raedt, Siegfried Nijssen, Barry O'Sullivan, and Pascal Van Hentenryck. Constraint Programming meets Machine Learning and Data Mining (Dagstuhl Seminar 11201). In Dagstuhl Reports, Volume 1, Issue 5, pp. 61-83, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2011)


Copy BibTex To Clipboard

@Article{deraedt_et_al:DagRep.1.5.61,
  author =	{De Raedt, Luc and Nijssen, Siegfried and O'Sullivan, Barry and Van Hentenryck, Pascal},
  title =	{{Constraint Programming meets Machine Learning and Data Mining (Dagstuhl Seminar 11201)}},
  pages =	{61--83},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2011},
  volume =	{1},
  number =	{5},
  editor =	{De Raedt, Luc and Nijssen, Siegfried and O'Sullivan, Barry and Van Hentenryck, Pascal},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagRep.1.5.61},
  URN =		{urn:nbn:de:0030-drops-32077},
  doi =		{10.4230/DagRep.1.5.61},
  annote =	{Keywords: Machine learning, data mining, constraint programming, constraints}
}
Document
08041 Abstracts Collection – Recurrent Neural Networks - Models, Capacities, and Applications

Authors: Luc De Raedt, Barbara Hammer, Pascal Hitzler, and Wolfgang Maass

Published in: Dagstuhl Seminar Proceedings, Volume 8041, Recurrent Neural Networks- Models, Capacities, and Applications (2008)


Abstract
From January 20 to 25 2008, the Dagstuhl Seminar 08041 ``Recurrent Neural Networks- Models, Capacities, and Applications'' was held in the International Conference and Research Center (IBFI), Schloss Dagstuhl. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general. Links to extended abstracts or full papers are provided, if available.

Cite as

Luc De Raedt, Barbara Hammer, Pascal Hitzler, and Wolfgang Maass. 08041 Abstracts Collection – Recurrent Neural Networks - Models, Capacities, and Applications. In Recurrent Neural Networks- Models, Capacities, and Applications. Dagstuhl Seminar Proceedings, Volume 8041, pp. 1-16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{deraedt_et_al:DagSemProc.08041.1,
  author =	{De Raedt, Luc and Hammer, Barbara and Hitzler, Pascal and Maass, Wolfgang},
  title =	{{08041 Abstracts Collection – Recurrent Neural Networks - Models, Capacities, and Applications}},
  booktitle =	{Recurrent Neural Networks- Models, Capacities, and Applications},
  pages =	{1--16},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8041},
  editor =	{Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.08041.1},
  URN =		{urn:nbn:de:0030-drops-14250},
  doi =		{10.4230/DagSemProc.08041.1},
  annote =	{Keywords: Recurrent Neural Networks, Neural-Symbolic Integration, Biological Models, Hybrid Models, Relational Learning Echo State Networks, Spike Prediction, Unsupervised Recurrent Networks}
}
Document
08041 Summary – Recurrent Neural Networks - Models, Capacities, and Applications

Authors: Luc De Raedt, Barbara Hammer, Pascal Hitzler, and Wolfgang Maass

Published in: Dagstuhl Seminar Proceedings, Volume 8041, Recurrent Neural Networks- Models, Capacities, and Applications (2008)


Abstract
The seminar centered around recurrent information processing in neural systems and its connections to brain sciences, on the one hand, and higher symbolic reasoning, on the other side. The goal was to explore connections across the disciplines and to tackle important questions which arise in all sub-disciplines such as representation of temporal information, generalization ability, inference, and learning.

Cite as

Luc De Raedt, Barbara Hammer, Pascal Hitzler, and Wolfgang Maass. 08041 Summary – Recurrent Neural Networks - Models, Capacities, and Applications. In Recurrent Neural Networks- Models, Capacities, and Applications. Dagstuhl Seminar Proceedings, Volume 8041, pp. 1-4, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{deraedt_et_al:DagSemProc.08041.2,
  author =	{De Raedt, Luc and Hammer, Barbara and Hitzler, Pascal and Maass, Wolfgang},
  title =	{{08041 Summary – Recurrent Neural Networks - Models, Capacities, and Applications}},
  booktitle =	{Recurrent Neural Networks- Models, Capacities, and Applications},
  pages =	{1--4},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8041},
  editor =	{Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.08041.2},
  URN =		{urn:nbn:de:0030-drops-14243},
  doi =		{10.4230/DagSemProc.08041.2},
  annote =	{Keywords: Recurrent networks}
}
Document
Equilibria of Iterative Softmax and Critical Temperatures for Intermittent Search in Self-Organizing Neural Networks

Authors: Peter Tino

Published in: Dagstuhl Seminar Proceedings, Volume 8041, Recurrent Neural Networks- Models, Capacities, and Applications (2008)


Abstract
Optimization dynamics using self-organizing neural networks (SONN) driven by softmax weight renormalization has been shown to be capable of intermittent search for high-quality solutions in assignment optimization problems. However, the search is sensitive to temperature setting in the softmax renormalization step. The powerful search occurs only at the critical temperature that depends on the problem size. So far the critical temperatures have been determined only by tedious trial-and-error numerical simulations. We offer a rigorous analysis of the search performed by SONN and derive analytical approximations to the critical temperatures. We demonstrate on a set of N-queens problems for a wide range of problem sizes N that the analytically determined critical temperatures predict the optimal working temperatures for SONN intermittent search very well.

Cite as

Peter Tino. Equilibria of Iterative Softmax and Critical Temperatures for Intermittent Search in Self-Organizing Neural Networks. In Recurrent Neural Networks- Models, Capacities, and Applications. Dagstuhl Seminar Proceedings, Volume 8041, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{tino:DagSemProc.08041.3,
  author =	{Tino, Peter},
  title =	{{Equilibria of Iterative Softmax and Critical Temperatures for Intermittent Search in Self-Organizing Neural Networks}},
  booktitle =	{Recurrent Neural Networks- Models, Capacities, and Applications},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8041},
  editor =	{Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.08041.3},
  URN =		{urn:nbn:de:0030-drops-14202},
  doi =		{10.4230/DagSemProc.08041.3},
  annote =	{Keywords: Recurrent self-organizing maps, symmetry breaking bifurcation, N-queens}
}
Document
Perspectives of Neuro--Symbolic Integration – Extended Abstract --

Authors: Kai-Uwe Kühnberger, Helmar Gust, and Peter Geibel

Published in: Dagstuhl Seminar Proceedings, Volume 8041, Recurrent Neural Networks- Models, Capacities, and Applications (2008)


Abstract
There is an obvious tension between symbolic and subsymbolic theories, because both show complementary strengths and weaknesses in corresponding applications and underlying methodologies. The resulting gap in the foundations and the applicability of these approaches is theoretically unsatisfactory and practically undesirable. We sketch a theory that bridges this gap between symbolic and subsymbolic approaches by the introduction of a Topos-based semi-symbolic level used for coding logical first-order expressions in a homogeneous framework. This semi-symbolic level can be used for neural learning of logical first-order theories. Besides a presentation of the general idea of the framework, we sketch some challenges and important open problems for future research with respect to the presented approach and the field of neuro-symbolic integration, in general.

Cite as

Kai-Uwe Kühnberger, Helmar Gust, and Peter Geibel. Perspectives of Neuro--Symbolic Integration – Extended Abstract --. In Recurrent Neural Networks- Models, Capacities, and Applications. Dagstuhl Seminar Proceedings, Volume 8041, pp. 1-6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{kuhnberger_et_al:DagSemProc.08041.4,
  author =	{K\"{u}hnberger, Kai-Uwe and Gust, Helmar and Geibel, Peter},
  title =	{{Perspectives of Neuro--Symbolic Integration – Extended Abstract --}},
  booktitle =	{Recurrent Neural Networks- Models, Capacities, and Applications},
  pages =	{1--6},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8041},
  editor =	{Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.08041.4},
  URN =		{urn:nbn:de:0030-drops-14226},
  doi =		{10.4230/DagSemProc.08041.4},
  annote =	{Keywords: Neuro-Symbolic Integration, Topos Theory, First-Order Logic}
}
Document
The Grand Challenges and Myths of Neural-Symbolic Computation

Authors: Luis C. Lamb

Published in: Dagstuhl Seminar Proceedings, Volume 8041, Recurrent Neural Networks- Models, Capacities, and Applications (2008)


Abstract
The construction of computational cognitive models integrating the connectionist and symbolic paradigms of artificial intelligence is a standing research issue in the field. The combination of logic-based inference and connectionist learning systems may lead to the construction of semantically sound computational cognitive models in artificial intelligence, computer and cognitive sciences. Over the last decades, results regarding the computation and learning of classical reasoning within neural networks have been promising. Nonetheless, there still remains much do be done. Artificial intelligence, cognitive and computer science are strongly based on several non-classical reasoning formalisms, methodologies and logics. In knowledge representation, distributed systems, hardware design, theorem proving, systems specification and verification classical and non-classical logics have had a great impact on theory and real-world applications. Several challenges for neural-symbolic computation are pointed out, in particular for classical and non-classical computation in connectionist systems. We also analyse myths about neural-symbolic computation and shed new light on them considering recent research advances.

Cite as

Luis C. Lamb. The Grand Challenges and Myths of Neural-Symbolic Computation. In Recurrent Neural Networks- Models, Capacities, and Applications. Dagstuhl Seminar Proceedings, Volume 8041, pp. 1-16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{lamb:DagSemProc.08041.5,
  author =	{Lamb, Luis C.},
  title =	{{The Grand Challenges  and Myths of Neural-Symbolic Computation}},
  booktitle =	{Recurrent Neural Networks- Models, Capacities, and Applications},
  pages =	{1--16},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8041},
  editor =	{Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.08041.5},
  URN =		{urn:nbn:de:0030-drops-14233},
  doi =		{10.4230/DagSemProc.08041.5},
  annote =	{Keywords: Connectionist non-classical logics, neural-symbolic computation, non-classical reasoning, computational cognitive models}
}
Document
The role of recurrent networks in neural architectures of grounded cognition: learning of control

Authors: Frank Van der Velde and Marc de Kamps

Published in: Dagstuhl Seminar Proceedings, Volume 8041, Recurrent Neural Networks- Models, Capacities, and Applications (2008)


Abstract
Recurrent networks have been used as neural models of language processing, with mixed results. Here, we discuss the role of recurrent networks in a neural architecture of grounded cognition. In particular, we discuss how the control of binding in this architecture can be learned. We trained a simple recurrent network (SRN) and a feedforward network (FFN) for this task. The results show that information from the architecture is needed as input for these networks to learn control of binding. Thus, both control systems are recurrent. We found that the recurrent system consisting of the architecture and an SRN or an FFN as a "core" can learn basic (but recursive) sentence structures. Problems with control of binding arise when the system with the SRN is tested on number of new sentence structures. In contrast, control of binding for these structures succeeds with the FFN. Yet, for some structures with (unlimited) embeddings, difficulties arise due to dynamical binding conflicts in the architecture itself. In closing, we discuss potential future developments of the architecture presented here.

Cite as

Frank Van der Velde and Marc de Kamps. The role of recurrent networks in neural architectures of grounded cognition: learning of control. In Recurrent Neural Networks- Models, Capacities, and Applications. Dagstuhl Seminar Proceedings, Volume 8041, pp. 1-18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{vandervelde_et_al:DagSemProc.08041.6,
  author =	{Van der Velde, Frank and de Kamps, Marc},
  title =	{{The role of recurrent networks in neural architectures of grounded cognition: learning of control}},
  booktitle =	{Recurrent Neural Networks- Models, Capacities, and Applications},
  pages =	{1--18},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8041},
  editor =	{Luc De Raedt and Barbara Hammer and Pascal Hitzler and Wolfgang Maass},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.08041.6},
  URN =		{urn:nbn:de:0030-drops-14213},
  doi =		{10.4230/DagSemProc.08041.6},
  annote =	{Keywords: Grounded representations, binding control, combinatorial structures, neural architecture, recurrent network, learning}
}
Document
07161 Abstracts Collection – Probabilistic, Logical and Relational Learning - A Further Synthesis

Authors: Luc De Raedt, Thomas Dietterich, Lise Getoor, Kristian Kersting, and Stephen H. Muggleton

Published in: Dagstuhl Seminar Proceedings, Volume 7161, Probabilistic, Logical and Relational Learning - A Further Synthesis (2008)


Abstract
From April 14 – 20, 2007, the Dagstuhl Seminar 07161 ``Probabilistic, Logical and Relational Learning - A Further Synthesis'' was held in the International Conference and Research Center (IBFI), Schloss Dagstuhl. During the seminar, several participants presented their current research, and ongoing work and open problems were discussed. Abstracts of the presentations given during the seminar as well as abstracts of seminar results and ideas are put together in this paper. The first section describes the seminar topics and goals in general. Links to extended abstracts or full papers are provided, if available.

Cite as

Luc De Raedt, Thomas Dietterich, Lise Getoor, Kristian Kersting, and Stephen H. Muggleton. 07161 Abstracts Collection – Probabilistic, Logical and Relational Learning - A Further Synthesis. In Probabilistic, Logical and Relational Learning - A Further Synthesis. Dagstuhl Seminar Proceedings, Volume 7161, pp. 1-21, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{deraedt_et_al:DagSemProc.07161.1,
  author =	{De Raedt, Luc and Dietterich, Thomas and Getoor, Lise and Kersting, Kristian and Muggleton, Stephen H.},
  title =	{{07161 Abstracts Collection – Probabilistic, Logical and Relational Learning - A Further Synthesis}},
  booktitle =	{Probabilistic, Logical and Relational Learning - A Further Synthesis},
  pages =	{1--21},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{7161},
  editor =	{Luc de Raedt and Thomas Dietterich and Lise Getoor and Kristian Kersting and Stephen H. Muggleton},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.07161.1},
  URN =		{urn:nbn:de:0030-drops-13885},
  doi =		{10.4230/DagSemProc.07161.1},
  annote =	{Keywords: Artificial Intelligence, Uncertainty in AI, Probabilistic Reasoning, Knowledge Representation, Logic Programming, Relational Learning, Inductive Logic Programming, Graphical Models, Statistical Relational Learning, First-Order Logical and Relational Probabilistic Languages}
}
Document
A general framework for unsupervised preocessing of structured data

Authors: Barbara Hammer, Alessio Micheli, and Alessandro Sperduti

Published in: Dagstuhl Seminar Proceedings, Volume 7161, Probabilistic, Logical and Relational Learning - A Further Synthesis (2008)


Abstract
We propose a general framework for unsupervised recurrent and recursive networks. This proposal covers various popular approaches like standard self organizing maps (SOM), temporal Kohonen maps, resursive SOM, and SOM for structured data. We define Hebbian learning within this general framework. We show how approaches based on an energy function, like neural gas, can be transferred to this abstract framework so that proposals for new learning algorithms emerge.

Cite as

Barbara Hammer, Alessio Micheli, and Alessandro Sperduti. A general framework for unsupervised preocessing of structured data. In Probabilistic, Logical and Relational Learning - A Further Synthesis. Dagstuhl Seminar Proceedings, Volume 7161, pp. 1-6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{hammer_et_al:DagSemProc.07161.2,
  author =	{Hammer, Barbara and Micheli, Alessio and Sperduti, Alessandro},
  title =	{{A general framework for unsupervised preocessing of structured data}},
  booktitle =	{Probabilistic, Logical and Relational Learning - A Further Synthesis},
  pages =	{1--6},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{7161},
  editor =	{Luc de Raedt and Thomas Dietterich and Lise Getoor and Kristian Kersting and Stephen H. Muggleton},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.07161.2},
  URN =		{urn:nbn:de:0030-drops-13837},
  doi =		{10.4230/DagSemProc.07161.2},
  annote =	{Keywords: Relational clustering, median clustering, recursive SOM models, kernel SOM}
}
Document
Exploiting prior knowledge in Intelligent Assistants - Combining relational models with hierarchies

Authors: Sriraam Natarajan, Prasad Tadepalli, and Alan Fern

Published in: Dagstuhl Seminar Proceedings, Volume 7161, Probabilistic, Logical and Relational Learning - A Further Synthesis (2008)


Abstract
Statitsical relational models have been successfully used to model static probabilistic relationships between the entities of the domain. In this talk, we illustrate their use in a dynamic decison-theoretic setting where the task is to assist a user by inferring his intentional structure and taking appropriate assistive actions. We show that the statistical relational models can be used to succintly express the system's prior knowledge about the user's goal-subgoal structure and tune it with experience. As the system is better able to predict the user's goals, it improves the effectiveness of its assistance. We show through experiments that both the hierarchical structure of the goals and the parameter sharing facilitated by relational models significantly improve the learning speed.

Cite as

Sriraam Natarajan, Prasad Tadepalli, and Alan Fern. Exploiting prior knowledge in Intelligent Assistants - Combining relational models with hierarchies. In Probabilistic, Logical and Relational Learning - A Further Synthesis. Dagstuhl Seminar Proceedings, Volume 7161, pp. 1-2, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2008)


Copy BibTex To Clipboard

@InProceedings{natarajan_et_al:DagSemProc.07161.3,
  author =	{Natarajan, Sriraam and Tadepalli, Prasad and Fern, Alan},
  title =	{{Exploiting prior knowledge in Intelligent Assistants - Combining relational models with hierarchies}},
  booktitle =	{Probabilistic, Logical and Relational Learning - A Further Synthesis},
  pages =	{1--2},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{7161},
  editor =	{Luc de Raedt and Thomas Dietterich and Lise Getoor and Kristian Kersting and Stephen H. Muggleton},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/DagSemProc.07161.3},
  URN =		{urn:nbn:de:0030-drops-13856},
  doi =		{10.4230/DagSemProc.07161.3},
  annote =	{Keywords: Statistical Relational Learning, Intelligent Assistants}
}
  • Refine by Author
  • 11 De Raedt, Luc
  • 4 Muggleton, Stephen H.
  • 3 Getoor, Lise
  • 3 Hammer, Barbara
  • 2 Cussens, James
  • Show More...

  • Refine by Classification
  • 2 Computing methodologies → Machine learning
  • 1 Computing methodologies → Artificial intelligence
  • 1 Human-centered computing → Human computer interaction (HCI)
  • 1 Software and its engineering → Compilers

  • Refine by Keyword
  • 3 Statistical Relational Learning
  • 2 Inductive Logic Programming
  • 2 Machine learning
  • 2 Statistical relational learning
  • 2 constraint programming
  • Show More...

  • Refine by Type
  • 33 document

  • Refine by Publication Year
  • 16 2008
  • 11 2006
  • 2 2019
  • 1 2011
  • 1 2015
  • Show More...

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail