Filters








8,111 Hits in 6.7 sec

An example distribution for probabilistic query learning of simple deterministic languages

Yasuhiro Tajima, Genichiro Kikui
2014 International Conference on Grammatical Inference  
At first, we show a learning algorithm of simple deterministic languages from membership and equivalence queries.  ...  In this paper, we show a special example distribution on which the learner can guess a correct simple deterministic grammar in polynomial time from membership queries and random examples.  ...  In this paper, we show a special example distribution for polynomial probabilistic learning of simple deterministic languages.  ... 
dblp:conf/icgi/TajimaK14 fatcat:mrbgnantc5g4fndffyht2cpx3u

The principles and practice of probabilistic programming

Noah D. Goodman
2013 Proceedings of the 40th annual ACM SIGPLAN-SIGACT symposium on Principles of programming languages - POPL '13  
For an example of this, we need look no further than the fundamental operation for inference, probabilistic conditioning, which forms a posterior distribution over executions from the prior distribution  ...  If we view the semantics of the underlying deterministic language as a map from programs to executions of the program, the semantics of the probabilistic language will be a map from programs to distributions  ...  Acknowledgments Thanks to Dan Roy, Cameron Freer, and Andreas Stuhlmüller for helpful comments. This work was supported by ONR grant N00014-09-0124.  ... 
doi:10.1145/2429069.2429117 dblp:conf/popl/Goodman13 fatcat:fv5rsbfz5rfp7fytwwt75xv25m

The principles and practice of probabilistic programming

Noah D. Goodman
2013 SIGPLAN notices  
For an example of this, we need look no further than the fundamental operation for inference, probabilistic conditioning, which forms a posterior distribution over executions from the prior distribution  ...  If we view the semantics of the underlying deterministic language as a map from programs to executions of the program, the semantics of the probabilistic language will be a map from programs to distributions  ...  Acknowledgments Thanks to Dan Roy, Cameron Freer, and Andreas Stuhlmüller for helpful comments. This work was supported by ONR grant N00014-09-0124.  ... 
doi:10.1145/2480359.2429117 fatcat:ez3zc3r2mrcpvjo7q4vqo27lhe

Recent advances of grammatical inference

Yasubumi Sakakibara
1997 Theoretical Computer Science  
Angluin [9] has shown that equivalence queries compensate for the lack of representative samples, and presented an efficient inference algorithm for identifying DFAs using equivalence and membership queries  ...  In this paper, we provide a survey of recent advances in the field "Grammatical Inference" with a particular emphasis on the results concerning the learnability of target classes represented by deterministic  ...  We also greatly thank our colleagues at the Machine Learning group at Fujitsu Labs., Hiroki Ishizaka (currently, at Kyushu Institute of Technology), Takeshi Koshiba, Masahiro Matsuoka, Yuji Takada, and  ... 
doi:10.1016/s0304-3975(97)00014-5 fatcat:4a4minst2nerti32iagjxf25ty

PAC Learning of Some Subclasses of Context-Free Grammars with Basic Distributional Properties from Positive Data [chapter]

Chihiro Shibata, Ryo Yoshinaka
2013 Lecture Notes in Computer Science  
This paper shows that several subclasses of contextfree languages that are known to be exactly learnable with membership queries by distributional learning techniques are pac learnable from positive data  ...  In recent years different interesting subclasses of cfls have been found to be learnable by techniques generically called distributional learning.  ...  Introduction To find an interesting subclass of context-free languages (cfls) that can provably be learned efficiently is an important topic in grammatical inference for several applications including  ... 
doi:10.1007/978-3-642-40935-6_11 fatcat:fkr3eznpxvhttei6tl3h7pio5e

10 Years of Probabilistic Querying – What Next? [chapter]

Martin Theobald, Luc De Raedt, Maximilian Dylla, Angelika Kimmig, Iris Miliaraki
2013 Lecture Notes in Computer Science  
While probabilistic databases have focused on describing tractable query classes based on the structure of query plans and data lineage, probabilistic programming has contributed sophisticated inference  ...  Both fields have developed their own variants of-both exact and approximate-top-k algorithms for query evaluation, and both investigate query optimization techniques known from SQL, Datalog, and Prolog  ...  Chapter 4 presents an algorithm that compiles theories in CNF into FO-da-DNNF. .1b is decomposable (Example 3.10) and automorphic (Example 3.14), but not deterministic (Example 3.11).  ... 
doi:10.1007/978-3-642-40683-6_1 fatcat:lofuquzqgbb4hcjtjeqydyakbe

Declarative Data Generation with ProbLog

Anton Dries
2015 Proceedings of the Sixth International Symposium on Information and Communication Technology - SoICT 2015  
To this end, we extend the ProbLog language with continuous distributions and we develop a simple sampling algorithm for this language.  ...  We demonstrate that many data generation tasks can be described as a model in this language and we provide examples of generators for attribute-value data, sequences, graphs and logical interpretations  ...  For example, Church [14] is a probabilistic programming language designed for the description of generative models.  ... 
doi:10.1145/2833258.2833267 dblp:conf/soict/Dries15 fatcat:2nbf6cyx4rf4pidnyqwsbgkj3m

Probabilistic Program Abstractions [article]

Steven Holtzen and Todd Millstein and Guy Van den Broeck
2017 arXiv   pre-print
At the heart of program abstraction is the relationship between a concrete program, which is difficult to analyze, and an abstract program, which is more tractable.  ...  Abstraction is a fundamental tool for reasoning about complex systems. Program abstraction has been utilized to great effect for analyzing deterministic programs.  ...  We begin by defining a simple probabilistic programming language. Syntactically, our probabilistic predicate abstractions will simply be probabilistic programs in this language.  ... 
arXiv:1705.09970v2 fatcat:vryjp63wlnaghc6pabhkdviumq

Learning a Compositional Semantics for Freebase with an Open Predicate Vocabulary

Jayant Krishnamurthy, Tom M. Mitchell
2015 Transactions of the Association for Computational Linguistics  
We present an approach to learning a model-theoretic semantics for natural language tied to Freebase.  ...  This logical form is evaluated against a learned probabilistic database that defines a distribution over denotations for each textual predicate.  ...  We additionally thank Matt Gardner, Ndapa Nakashole, Amos Azaria and the anonymous reviewers for their helpful comments.  ... 
doi:10.1162/tacl_a_00137 fatcat:vuoo5747drfkdmjaa344kdli6q

Implementing a Library for Probabilistic Programming Using Non-strict Non-determinism

SANDRA DYLUS, JAN CHRISTIANSEN, FINN TEEGEN
2019 Theory and Practice of Logic Programming  
For example, the concepts of non-deterministic choice and call-time choice as known from functional logic programming are related to and coincide with stochastic memoization and probabilistic choice in  ...  It demonstrates how the concepts of a functional logic programming language support the implementation of a library for probabilistic programming.  ...  As an example for the use of (??)  ... 
doi:10.1017/s1471068419000085 fatcat:32fav6eltrg3lft4tpdagi5are

Identifiability of Model Properties in Over-Parameterized Model Classes [chapter]

Manfred Jaeger
2013 Lecture Notes in Computer Science  
Classical learning theory is based on a tight linkage between hypothesis space (a class of function on a domain X), data space (function-value examples (x, f (x))), and the space of queries for the learned  ...  model (predicting function values for new examples x).  ...  With an increasing ambition of learning models in more and more expressive model classes, for example probabilistic programming languages [12, 7, 5] , one also encounters more and more complex relationships  ... 
doi:10.1007/978-3-642-40994-3_8 fatcat:7mqtsmxjqnhqleh5b2kb2ifctu

Implementing a Library for Probabilistic Programming using Non-strict Non-determinism [article]

Sandra Dylus, Jan Christiansen, Finn Teegen
2019 arXiv   pre-print
For example, the concepts of non-deterministic choice and call-time choice as known from functional logic programming are related to and coincide with stochastic memoization and probabilistic choice in  ...  It demonstrates how the concepts of a functional logic programming language support the implementation of a library for probabilistic programming.  ...  Finally, we are thankful for the comments of the anonymous reviewers to improve the readability of this paper.  ... 
arXiv:1905.07212v1 fatcat:75a2fmqfyzgojbchp6jx6nbwru

Inferring Temporal Compositions of Actions Using Probabilistic Automata [article]

Rodrigo Santa Cruz, Anoop Cherian, Basura Fernando, Dylan Campbell, Stephen Gould
2020 arXiv   pre-print
Specifically, we propose to express temporal compositions of actions as semantic regular expressions and derive an inference framework using probabilistic automata to recognize complex actions as satisfying  ...  Our approach is different from existing works that either predict long-range complex activities as unordered sets of atomic actions, or retrieve videos using natural language sentences.  ...  Acknowledgements: This research was supported by the Australian Research Council Centre of Excellence for Robotic Vision (CE140100016).  ... 
arXiv:2004.13217v1 fatcat:lk2qzs3iezfl7lubwjbqfu6zby

Complex Event Processing Under Uncertainty: A Short Survey

Elias Alevizos, Anastasios Skarlatidis, Alexander Artikis, Georgios Paliouras
2015 International Conference on Extending Database Technology  
A number of limitations are identified with respect to the employed languages, their probabilistic models and their performance, as compared to the purely deterministic cases.  ...  Complex Event Recognition (CER) applications exhibit various types of uncertainty, ranging from incomplete and erroneous data streams to imperfect complex event patterns.  ...  A simple example from the domain of video recognition is the query in which the user asks about the most probable time interval during which a certain activity occurs.  ... 
dblp:conf/edbt/Alevizos15 fatcat:r4hfpbiab5bzvdcqmdn6b646oi

Page 4079 of Mathematical Reviews Vol. , Issue 2004e [page]

2004 Mathematical Reviews  
The author gives an example of a Boolean function for which a quantum branching program is provably much better than a deterministic or probabilistic stable one: namely, for a function MOD, that checks  ...  This, in particular, gives a learning algorithm for an O(logn)-depth decision tree from membership queries only and a new learning algorithm of any multivariate polynomial over sufficiently large fields  ... 
« Previous Showing results 1 — 15 out of 8,111 results