A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
Inference with Multinomial Tests p. 149 Learning Languages with Help p. 161 Incremental Learning of Context Free Grammars p. 174 Estimating Grammar Parameters Using Bounded Memory p. 185 Stochastic ... Languages p. 283 Software Descriptions The EMILE 4.1 Grammar Induction Toolbox p. 293 Software for Analysing Recurrent Neural Nets That Learn to Predict Non-regular Languages p. 296 A Framework ...doi:10.1007/3-540-45790-9_6 fatcat:nmlknwqoyfbybhb6rpomqrn7qy
A fuzzy automaton behaves in a deterministic fashion. However, it has many properties similar to those of stochastic automata. Its application as a model of learning systems is discussed. ... T. 9670 Linear regular languages. I. Acta Cybernet’ 1 (1969), 3-12. ...
Lecture Notes in Computer Science
They cover the areas of polynomial learning models, learning from ordered alphabets, learning deterministic Pomdps, learning negotiation processes, learning from context-free background knowledge. ... Work with Henning Fernau on polynomial learning is where the ideas in section 3 come from. Philippe Jaillon gave me the initial ideas for the negotiation problem in section 9. Discussions with ... Testing equivalence of regular deterministic distributions Learning stochastic languages is an important topic in grammatical inference. ...doi:10.1007/11872436_4 fatcat:5snm4lpumbhw5e7ffh5vwxzhum
The field of grammatical inference (also known as grammar induction) is transversal to a number of research areas including machine learning, formal language theory, syntactic and structural pattern recognition ... Therefore, learning a stochastic automaton involves a modification of bias from what has been presented before: even if the underlying language is regular, the distribution may not be. ... The theory The main focus of research in the field of grammatical inference has been set on learning regular grammars or deterministic finite automata (DFA). ...doi:10.1016/j.patcog.2005.01.003 fatcat:62qwskiqcvddjobakbdshwebqq
S. 57 + 11976 Learning with stochastic automata and stochastic languages. With discussion. Computer oriented learning processes (Proc. NATO Advanced Study Inst., Bonas, 1974), pp. 69-107. ... This paper contains a survey of learning algorithms for stochastic automata and inference procedures for stochastic grammars. ...
Unfortunately, there is no algorithm capable of learning the complete class of deterministic regular expressions from positive examples only, as we will show. ... Inferring an appropriate DTD or XML Schema Definition (XSD) for a given collection of XML documents essentially reduces to learning deterministic regular expressions from sets of positive example words ... Since deterministic regular expressions like a * define infinite languages, and since every non-empty finite language can be defined by a deterministic expression (as we show in the full version of this ...doi:10.1145/1841909.1841911 fatcat:hre7agfyuzhudl3xwlaxxd4xg4
Unfortunately, there is no algorithm capable of learning the complete class of deterministic regular expressions from positive examples only, as we will show. ... Inferring an appropriate DTD or XML Schema Definition (XSD) for a given collection of XML documents essentially reduces to learning deterministic regular expressions from sets of positive example words ... Since deterministic regular expressions like a * define infinite languages, and since every non-empty finite language can be defined by a deterministic expression (as we show in the full version of this ...doi:10.1145/1367497.1367609 dblp:conf/www/BexGNV08 fatcat:bqs6npqyi5eaxlzv5n3ktgb6di
In this paper, we propose to use the Wasserstein autoencoder (WAE) for probabilistic sentence generation, where the encoder could be either stochastic or deterministic. ... the stochasticity of the encoder. ... D and S refer to the deterministic and stochastic encoders, respectively. ↑/↓ The larger/lower, the better. ...doi:10.18653/v1/n19-1411 dblp:conf/naacl/BahuleyanMZV19 fatcat:y5cetx4ct5hdjcr6x4ibeequ4y
Mungojerrie (https://plv.colorado.edu/mungojerrie/) is a tool for testing reward schemes for ω-regular objectives on finite models. ... An alternative to this manual programming, akin to programming directly in assembly, is to specify the objective in a formal language and have it "compiled" to a reward scheme. ... A natural choice for this language is Linear Temporal Logic (LTL) [22, 27] , or more generally, ω-regular languages  . ω-regular languages describe infinite sequences. ...arXiv:2106.09161v2 fatcat:k7jvqed2wzebfbthfg2zwhxzo4
Lecture Notes in Computer Science
Sparsity is a potentially important property of neural networks, but is not explicitly controlled by Dropout-based regularization. ... Sparseout provides a way to investigate sparsity in state-of-the-art deep learning models. Source code for Sparseout could be found at . ... Stochastic regularization has become the standard practice in training deep learning models and have outperformed deterministic regularization methods on many tasks. ...doi:10.1007/978-3-030-18305-9_24 fatcat:6kc7pdzm2zhxnc5mxutdiogu3y
This enables composition via a unified abstraction over deterministic and stochastic functions and allows for scalability via the underlying system. ... Finally, we show how Bayesian Layers can be used within the Edward2 probabilistic programming language for probabilistic programs with stochastic processes. ... ., 2017 ) ( Figure 6 ); or an auto-encoder with stochastic encoders and decoders (Figure 7) . 3 Signature To implement stochastic output layers, we perform deterministic computations given a tensordimensional ...arXiv:1812.03973v3 fatcat:oxsckegvezcfljz25nlz4cfn54
In this paper, the identification of stochastic regular languages is addressed. ... For this purpose, we propose a class of algorithms which allow for the identification of the structure of the minimal stochastic automaton generating the language. ... Every stochastic deterministic regular grammar G defines a stochastic deterministic regular language (SDRL), L G , through the probabilities p(w|L G ) = p(S ⇒ w). ...doi:10.1051/ita:1999102 fatcat:rw2vcb2qtnfo7ma5cns3dffuum
We prove that there are more languages generated by PRFA than by Probabilistic Deterministic Finite Automata (PDFA). ... We show that this class can be characterized by a simple intrinsic property of the stochastic languages they generate (the set of residual languages is finitely generated) and that it admits canonical ... It consists of all stochastic languages generated by probabilistic finite automata. Also, the class of stochastic deterministic regular languages on Σ is denoted by L P DF A (Σ). ...doi:10.1007/3-540-45790-9_7 fatcat:go6ap7enwjhnflnwve4ayalj74
This is a direct consequence of the fact that every regular language is the support of at least one stochastic regular language, and there are regular languages which are not k-testable. ... APPENDIX A.1 Proof of Theorem 3Theorem 3 (Stochastic morphism theorem). Let AE be a finite alphabet and D be a stochastic regular language on AE ? . ...doi:10.1109/tpami.2005.148 pmid:16013757 fatcat:vaoopt4ypzffzpv53pxx2hodpy
We propose a general setting to deal with these cases and provide algorithms that can learn deterministic finite automata in these conditions. ... Grammatical inference consists in learning formal grammars for unknown languages when given learning data. Classically this data is raw: strings that belong to the language or that do not. ... An interesting alternative is to consider the hypothesis that not only is the language regular, but that the distribution also is. In such a case one needs to learn a Stochastic Finite Automaton. ...doi:10.1007/3-540-45790-9_13 fatcat:adbjrahojfejxieqmglom6vnay
« Previous Showing results 1 — 15 out of 13,779 results