2,588 Hits in 5.6 sec

Developments from enquiries into the learnability of the pattern languages from positive data

Yen Kaow Ng, Takeshi Shinohara
2008 Theoretical Computer Science  
The pattern languages are languages that are generated from patterns, and were first proposed by Angluin as a non-trivial class that is inferable from positive data [D.  ...  Angluin, Finding patterns common to a set of strings, Journal of Computer and System Sciences 21 (1980) 46-62; D.  ...  Theorem 25 (Theorem 19 and 20 in [57] ). (1) The class of unbounded unions of (erasing or non-erasing) languages generated from proper regular patterns is not learnable from positive data. (2) The class  ... 
doi:10.1016/j.tcs.2008.02.028 fatcat:wphpibt575e7rdx6rb4l6if2c4

Learning indexed families of recursive languages from positive data: A survey

Steffen Lange, Thomas Zeugmann, Sandra Zilles
2008 Theoretical Computer Science  
Such language classes are of interest because of their naturalness.  ...  This model has been studied for learning recursive functions, recursively enumerable languages, and recursive languages, reflecting different aspects of machine learning, artificial intelligence, complexity  ...  Acknowledgments We thank the anonymous referees for their very careful reading and their numerous suggestions. Many thanks are also due to Robert Holte for his comments on a draft version.  ... 
doi:10.1016/j.tcs.2008.02.030 fatcat:jzsqdyddvrbz3bhwxeukqnrty4

Segmentation from 97% to 100%: Is It Time for Some Linguistics?

Petr Sojka
2012 Recent Advances in Slavonic Natural Languages Processing  
We formally define this task and prove that it is in the class of non-polynomial optimization problems.  ...  We evaluate methodology of using competing patterns for these tasks and decide on the complexity of creation of space-optimal (minimal) patterns that completely (100 %) implement the segmentation task.  ...  Acknowledgements This work has been partially supported by the European Union through its Competitiveness and Innovation Programme (Information and Communications Technologies Policy Support Programme,  ... 
dblp:conf/raslan/Sojka12 fatcat:6icidfknejhkxkw5zddrjczexe

Extending Elementary Formal Systems [chapter]

Steffen Lange, Gunter Grieser, Klaus P. Jantke
2001 Lecture Notes in Computer Science  
Moreover, we investigate the learnability of the corresponding AEFS definable language classes in two major learning paradigms, namely in Gold's model of learning in the limit and Valiant's model of probably  ...  We study the expressiveness of this approach by comparing certain AEFS definable language classes to the levels in the Chomsky hierarchy and to the language classes that are definable by EFSs that meet  ...  Although the considered classes of AEFS definable languages properly comprise the corresponding classes of EFS definable languages -which are the largest classes of EFS definable languages formerly known  ... 
doi:10.1007/3-540-45583-3_25 fatcat:mx7vo3wmejdzdhsh54ux7pzp5m

Advanced elementary formal systems

Steffen Lange, Gunter Grieser, Klaus P. Jantke
2003 Theoretical Computer Science  
Moreover, we investigate the learnability of the corresponding AEFS deÿnable language classes in two major learning paradigms, namely in Gold's model of learning in the limit and Valiant's model of probably  ...  We study the expressiveness of this approach by comparing certain AEFS deÿnable language classes to the levels in the Chomsky hierarchy and to the language classes that are deÿnable by EFSs that meet the  ...  Acknowledgements This work has been partially supported by the German Ministry of Economics and Technology (BMWi) within the joint project LExIKON under grants 01 MD 948 and 01 MD 949.  ... 
doi:10.1016/s0304-3975(02)00418-8 fatcat:vkay4rg7sreydpftlbd4lh27ni

Two-Dimensional Pattern Languages [article]

Henning Fernau, Markus L. Schmid, K. G. Subramanian
2017 arXiv   pre-print
These classes of two-dimensional pattern languages are compared with respect to their expressive power and their closure properties are investigated.  ...  We introduce several classes of array languages obtained by generalising Angluin's pattern languages to the two-dimensional case.  ...  what the appropriate two-dimensional counterpart of the class of regular languages might be (see Giammarresi et al  ... 
arXiv:1707.04083v1 fatcat:ecs6yxe72ra6dekj7i3y42pjxa

Inferring descriptive generalisations of formal languages

Dominik D. Freydenberger, Daniel Reidenbach
2013 Journal of computer and system sciences (Print)  
generalisations within a class of pattern languages.  ...  Note that L Σ is an infinite language (and, in fact, an infinite union of languages from ePAT tf,Σ ).  ...  Acknowledgements The authors wish to thank Steffen Lange for his helpful remarks and suggestions on the inference model and some results presented in this paper.  ... 
doi:10.1016/j.jcss.2012.10.001 fatcat:y7qydesy2banlhv23tewazn6my

Knowledge Representation in Bicategories of Relations [article]

Evan Patterson
2017 arXiv   pre-print
Although we make extensive use of categorical language, this paper is designed to be self-contained and has considerable expository content.  ...  The only prerequisites are knowledge of first-order logic and the rudiments of category theory.  ...  Acknowledgments I thank John Baez, David Spivak, and Ryan Wisnesky for helpful comments on the manuscript. I am grateful to Thomas Icard for his encouragement of this project.  ... 
arXiv:1706.00526v2 fatcat:iyr2xxdteveqzlzjy6l6gq73oe

High-dimensional separability for one- and few-shot learning [article]

Alexander N. Gorban, Bogdan Grechuk, Evgeny M. Mirkes, Sergey V. Stasenko, Ivan Y. Tyukin
2021 arXiv   pre-print
New multi-correctors of AI systems are presented and illustrated with examples of predicting errors and learning new classes of objects by a deep convolutional neural network.  ...  Separation theorems in infinite-dimensional limits are proven under assumptions of compact embedding of patterns into data space.  ...  When we select this compact and apply whitening, it becomes a new universe and we see a set of compact patterns inside, etc. Figure 7 . 7 Clustered universe in learning a new class.  ... 
arXiv:2106.15416v1 fatcat:fmxx7pdfenflth4ec2a54cucpe

Designing neural networks through neuroevolution

Kenneth O. Stanley, Jeff Clune, Joel Lehman, Risto Miikkulainen
2019 Nature Machine Intelligence  
and hybridization to the deep learning, deep reinforcement learning and machine learning communities, and to explain how neuroevolution could prove to be a critical tool in the long-term pursuit of artificial  ...  Neuroevolution also differs from deep learning (and deep reinforcement learning) by maintaining a population of solutions during search, enabling extreme exploration and massive parallelization.  ...  For example, the positions of sensor and motor neurons within a quadruped body can be exploited to efficiently evolve regular gait patterns 46 , which require regular connectivity patterns unrelated  ... 
doi:10.1038/s42256-018-0006-z fatcat:gkcu2s7bjvhnxotnhexpwpdyzu

Cost-to-Go Function Approximation [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
It maintains a set, S , of most specific hypotheses that are consistent with the training data and a set, G, of most general hypotheses consistent with the training data.  ...  Some algorithms, most notably CN2 (Clark and Niblett 1989; Clark and Boswell 1991) , learn multi-class rules directly by optimizing overall possible classes in the head of the rule.  ...  framework, i.e., they assume a set of positive and negative training examples.  ... 
doi:10.1007/978-1-4899-7687-1_100093 fatcat:vse7ncdqs5atlosjhz7fhlj3im

Ad Hoc Data and the Token Ambiguity Problem [chapter]

Qian Xi, Kathleen Fisher, David Walker, Kenny Q. Zhu
2008 Lecture Notes in Computer Science  
PADS is a declarative language used to describe the syntax and semantic properties of ad hoc data sources such as financial transactions, server logs and scientific data sets.  ...  The PADS compiler reads these descriptions and generates a suite of useful data processing tools such as format translators, parsers, printers and even a query engine, all customized to the ad hoc data  ...  It takes time for new users to learn the language syntax and even experienced users can take hours or days to develop descriptions for complex formats.  ... 
doi:10.1007/978-3-540-92995-6_7 fatcat:yravsj6fz5fkdmalyzs4ph3us4

Subject index volumes 1–200

1999 Theoretical Computer Science  
, 674,694,747, 1081, 1157, 1678, 1832 union of BCNF families, 529 union of congruence classes, 406 in a monoid, finite -, 329 union of groups, 52 languages, 201 SBTA-languages, 3336 states, 283  ...  , usual -, 2995 properties of -, 2789 uniformizing strategies, 2663 uniformly continuous endofunctions. 2995 defined families of categories, 1700 erasable families of languages, 26 growing k-th  ... 
doi:10.1016/s0304-3975(98)00319-3 fatcat:s22ud3iiqjht7lfbtc3zctk7zm


L.A. Zadeh
1975 Fuzzy Sets and their Applications to Cognitive and Decision Processes  
In terms of such restrictions, the meaning of a proposition of the form "x is P," where x is the name of an object and P is a fuzzy set, may be expressed as a relational assignment equation of the form  ...  The calculus of fuzzy restrictions is concerned, in the main, with (a) translation of propositions of various types into relational assignment equations, and (b) the study of transformations of fuzzy restrictions  ...  Wee and Fu [7] have formulated a class of fuzzy automata and discussed its application to pattern recognition with non-supervised learning.  ... 
doi:10.1016/b978-0-12-775260-0.50006-2 fatcat:zhkupyhimzcaffxqgadlfom2zq


Cen Rao, Alper Yilmaz, Mubarak Shah
2012 International Journal of Computer Vision  
This representation is compact, view-invariant, and is capable of explaining an action in terms of meaningful action units called dynamic instants and intervals.  ...  Starting without a model, we use this representation for recognition and incremental learning of human actions.  ...  Xin Li and Khurram Shafique for their valuable comments and discussions.  ... 
doi:10.1023/a:1020350100748 fatcat:u2d3rhp3qrdcxeq4nkvzxsnrtm
« Previous Showing results 1 — 15 out of 2,588 results