Filters








652 Hits in 7.3 sec

Probabilistic Reasoning across the Causal Hierarchy [article]

Duligur Ibeling, Thomas Icard
2021 arXiv   pre-print
We propose a formalization of the three-tier causal hierarchy of association, intervention, and counterfactuals as a series of probabilistic logical languages.  ...  We give a corresponding series of finitary axiomatizations complete over both structural causal models and probabilistic programs, and show that satisfiability and validity for each language are decidable  ...  DGE-1656518, and by the Center for the Study of Language and Information.  ... 
arXiv:2001.02889v5 fatcat:y35w6gyjybhsnevhujmlzieju4

Probabilistic Reasoning Across the Causal Hierarchy

Duligur Ibeling, Thomas Icard
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We propose a formalization of the three-tier causal hierarchy of association, intervention, and counterfactuals as a series of probabilistic logical languages.  ...  We give a corresponding series of finitary axiomatizations complete over both structural causal models and probabilistic programs, and show that satisfiability and validity for each language are decidable  ...  These three modes of reasoning constitute a causal hierarchy (Shpitser and Pearl 2008; Pearl 2009) , highlighting the significance of structural causal knowledge for flexible thought and action.  ... 
doi:10.1609/aaai.v34i06.6577 fatcat:mmu64kwb4zfkxahiq7site3b2a

Instantiating Sapience: An Inquiry into Reason

Andrea Giuseppe Ragno
2019 Deutsche Jahrestagung für Künstliche Intelligenz  
In the second section, I provide a quick genealogy of the theory of mind that I find most useful for this project, i.e. functionalism.  ...  In what follows I offer a brief methodological perspective on the project about the implementation of sapient conceptual skills in technical devices, i.e. part of what has been defined as Artificial General  ...  of a probabilistic expression [19] .  ... 
dblp:conf/ki/Ragno19 fatcat:pizbqlk6lfacdinwptabhpjz5a

On the Tractability of Neural Causal Inference [article]

Matej Zečević and Devendra Singh Dhami and Kristian Kersting
2021 arXiv   pre-print
We further introduce a new tractable NCM-class that is efficient in inference and fully expressive in terms of Pearl's Causal Hierarchy.  ...  Roth (1996) proved that any form of marginal inference with probabilistic graphical models (e.g. Bayesian Networks) will at least be NP-hard.  ...  Acknowledgements This work was supported by the ICT-48 Network of AI Research Excellence Center "TAILOR" (EU Horizon 2020, GA No 952215) and by the Federal Ministry of Education and Research (BMBF; project  ... 
arXiv:2110.12052v1 fatcat:khgxg2olebhdtnrpladcxyc7xq

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution [article]

Judea Pearl
2018 arXiv   pre-print
To demonstrate the essential role of such models, I will present a summary of seven tasks which are beyond reach of current machine learning systems and which have been accomplished using the tools of  ...  To achieve human level intelligence, learning machines need the guidance of a model of reality, similar to the ones used in causal inference tasks.  ...  This hierarchy, and the formal restrictions it entails, explains why statistics-based machine learning systems are prevented from reasoning about actions, experiments and explanations.  ... 
arXiv:1801.04016v1 fatcat:6pivrf5v7fgjdf3ckyw6cj6bse

Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models [article]

Matej Zečević, Devendra Singh Dhami, Athresh Karanam, Sriraam Natarajan, Kristian Kersting
2021 arXiv   pre-print
While probabilistic models are an important tool for studying causality, doing so suffers from the intractability of inference.  ...  As a step towards tractable causal models, we consider the problem of learning interventional distributions using sum-product networks (SPNs) that are over-parameterized by gate functions, e.g., neural  ...  This work was supported by the ICT-48 Network of AI Research Excellence Center "TAILOR" (EU Horizon 2020, GA No 952215) and by the Federal Ministry of Education and Research (BMBF; project "PlexPlain",  ... 
arXiv:2102.10440v5 fatcat:7instaliz5amblf42rdnxdnkay

Hypothetical revision and matter-of-fact supposition [article]

Horacio Arlo-Costa
2000 arXiv   pre-print
The notion of qualitative change of view that thus arises is axiomatized and compared with standard notions like AGM and UPDATE.  ...  The paper studies the notion of supposition encoded in non-Archimedean conditional probability (and revealed in the acceptance of the so-called indicative conditionals).  ...  Acknowledgements Thanks are due to Isaac Levi, Rohit Parikh, Judea Pearl, Teddy Seidenfeld, Richmond Thomason and Bas van Fraassen.  ... 
arXiv:cs/0003022v1 fatcat:6pcq6ntzwrgenijeu4qahrawdi

Page 1837 of Mathematical Reviews Vol. , Issue 98C [page]

1998 Mathematical Reviews  
Neelakantan Kartha and Viadimir Lifschitz, A simple formalization of actions using cir- cumscription (1970-1975); Norman McCain and Hudson Turner, A causal theory of ramifications and qualifications (1978  ...  for probabilistic and Bayesian logic (1862-1868); Philippe Smets, The canonical decomposition of a weighted belief (1896-1901); Ronald R.  ... 

Edited transcription of the workshop on defeasible reasoning with specificity and multiple inheritance St. Louis, April 1989

Jennie Dorosh, Ronald P. Loui
1990 ACM SIGART Bulletin  
Pearl: Yes, but isn't that justified probabilistically? McCarty: No, not probabilistically.  ...  This is not justified probabilistically. But it has the same type of sufficient and necessary conditions when you apply epsiion semantics to this type of network.  ... 
doi:10.1145/122388.122389 fatcat:xqpkc37n75biheym7vydc6w5zi

Object-Oriented Bayesian Networks [article]

Daphne Koller, Avi Pfeffer
2013 arXiv   pre-print
These attributes can themselves be objects, providing a natural framework for encoding part-of hierarchies.  ...  We use a Bayesian network fragment to describe the probabilistic relations between the attributes of an object.  ...  Acknowledgements We would like to thank Kathy Laskey for her great help in making some of our definitions more coherent.  ... 
arXiv:1302.1554v1 fatcat:wr7l4floa5ewjl3wizaik4gomy

Index—Volumes 1–89

1997 Artificial Intelligence  
88 proofs into English, translation of -88 formal reasoning 640, 1180 in continuous time 640 mechanized -152 formal semantics 622, 1086, 1268 for mutual belief 1086 formal signal processing models  ...  1186 specification 3 16, 1082 formal systems 445, 1036 intractability of -379 nonmonotonic -4 19 formal temporal reasoning 454,464 theories of action 496 formal theory 295 for plan merging 920  ...  mathematics of non-monotonic-150 mechanism 381 mechanized formal -152 meta-level -185 method geometric -12 17 methods choices of -1157 models inexact -906 multiple inheritance -966 multiple lines of -  ... 
doi:10.1016/s0004-3702(97)80122-1 fatcat:6az7xycuifaerl7kmv7l3x6rpm

Causal Reasoning and Meno's Paradox

Melvin Chen, Lock Yue Chew
2020 AI & Society: The Journal of Human-Centred Systems and Machine Intelligence  
of counterfactuals, then one relies besides on tacit knowledge, as might be constituted by or derived from the epistemic faculty virtues and abilities of the causal reasoner, the value systems and character  ...  While certain aspects of causal reasoning may be axiomatized and formalized and algorithms may be implemented to approximate causal reasoning, one has to remain skeptical about whether causal reasoning  ...  To view a copy of this licence, visit http://creat iveco mmons .org/licen ses/by/4.0/.  ... 
doi:10.1007/s00146-020-01037-4 fatcat:lwteng7vgjgsjaemobbsbhntca

Nonmonotonic probabilistic logics under variable-strength inheritance with overriding: Complexity, algorithms, and implementation

Thomas Lukasiewicz
2007 International Journal of Approximate Reasoning  
They are formalisms for probabilistic reasoning from sets of strict logical, default logical, and default probabilistic sentences, which are parameterized through a value k 2 [0, 1] that describes the  ...  Finally, I describe the system NMPROBLOG, which includes a prototype implementation of these algorithms.  ...  Acknowledgements This work was supported by a Heisenberg Professorship of the German Research Foundation (DFG).  ... 
doi:10.1016/j.ijar.2006.07.015 fatcat:ksokw6xt3vhtxjikdknduaaz4e

Team semantics for interventionist counterfactuals and causal dependence [article]

Fausto Barbero, Gabriel Sandu
2018 arXiv   pre-print
We introduce formal languages for both deterministic and probabilistic causal discourse, and study in some detail their inferential aspects.  ...  We suggest a way of dealing with such cases by 1) the introduction of formal entries in causal teams, and 2) the introduction of weaker truth values (falsifiability and admissibility), for which we suggest  ...  Galles and Pearl ([8] ) consider the case of systems with unique solutions, defined as follows: 1) for fixed values of the exogenous variables, the system has a unique solution, and 2) each "intervened  ... 
arXiv:1712.08661v3 fatcat:miywxf3ycreqvnqtjbfpmyelte

A hierarchical Bayesian framework for multimodal active perception

João Filipe Ferreira, Miguel Castelo-Branco, Jorge Dias
2012 Adaptive Behavior  
simpler building blocks; seamless integration of additional inputs is allowed by the Bayesian Programming formalism; initial 'genetic imprint' of distribution parameters may be changed 'on the fly' through  ...  Its composing models build upon a common spatial configuration that is naturally fitting for the integration of readings from multiple sensors using a Bayesian approach devised in previous work.  ...  Acknowledgement The authors would particularly like to thank, at the Institute of Systems and Robotics (ISR/FCT-UC), Pedro Trindade for developing the Blender-based BVM viewer software and Joa˜o Quintas  ... 
doi:10.1177/1059712311434662 fatcat:izkpgww2zzbltdaidq26oejmru
« Previous Showing results 1 — 15 out of 652 results