PL
 |
EN
Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl
Ograniczanie wyników
Czasopisma help
  1. 8 Studia Informatica
  2. 3 Discussiones Mathematicae Probability and Statistics
  3. 2 Adam Mickiewicz University Law Review
  4. 2 Filosofický časopis (Philosophical Journal)
  5. 2 Journal of Language Modelling
Więcej...
Lata help
  1. 2 2023
  2. 1 2022
  3. 3 2021
  4. 3 2019
  5. 3 2018
Więcej...
Autorzy help
  1. 6 Simiński R.
  2. 3 Koszowski M.
  3. 3 Nowak-Brzezińska A.
  4. 2 Ficoń K.
  5. 2 Jach T.
Więcej...
Preferencje help
Polish version English version Język
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 55

Liczba wyników na stronie
first rewind previous Strona / 3 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  inference
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 3 next fast forward last
1
Content available remote Decomposition and Approximation of Loopy Bayesian Networks
100%
Dong J. , Chen F. , Huo Y. , Liu H.
Fundamenta Informaticae
|
2013
|
tom Vol. 125, nr 2
135--152
EN
This paper proposes a new method, conditional probability table (CPT) decomposition, to analyze the independent and deterministic components of CPT. This method can be used to approximate and analyze Baysian networks. The decomposition of Bayesian networks is accomplished by representing CPTs as a linear combination of extreme CPTs, which forms a new framework to conduct inference. Based on this new framework, inference in Bayesian networks can be done by decomposing them into less connected and weighted subnetworks. We can achieve exact inference if the original network is decomposed into singly-connected subnetworks. Besides, approximate inference can be done by discarding the subnetworks with small weights or by a partial decomposition and application of belief propagation (BP) on the still multiply-connected subnetworks. Experiments show that the decomposition-based approximation outperforms BP in most cases.
2
Content available remote Selected aspects of the diagnostic process in rail transport
100%
Chrzan M. , Ciszewski T. , Nowakowski W.
Pojazdy Szynowe
|
2023
|
tom Nr 3-4
4--12
EN
The article presents selected results of research in the area of reducing the risk of defects in railway infrastructure and traffic control devices. The first part of the article will discuss selected topics used in a defectoscope car for automated ultrasonic rail inspections related to the identification of joints and flaws. A method based on the identification of joints and flaws using a neural network will be presented. The second part of the article will cover research on the automatic collection of diagnostic data from railway traffic control devices. The solutions presented concern a simulator of railway traffic control device malfunctions, from which data is extracted to populate a database of malfunctions and then used in the inference process. The article will present partial results of research on both systems.
3
Content available remote Logic, Reasoning, Argumentation: Insights from the Wild
100%
Zenker F.
Logic and Logical Philosophy
|
2018
|
tom 27
|
nr 4 Special Issue on Logic, Cognition, Argumentation. Guest Editors: Mariusz Urbański, Michiel van Lambalgen and Marcin Koszowy
421-451
EN
This article provides a brief selective overview and discussion of recent research into natural language argumentation that may inform the study of human reasoning on the assumption that an episode of argumentation issues an invitation to accept a corresponding inference. As this research shows, arguers typically seek to establish new consequences based on prior information. And they typically do so vis-à-vis a real or an imagined opponent, or an opponent-position, in ways that remain sensitive to considerations of context, audiences, and goals. Deductively valid inferences remain a limiting case of such reasoning. In view of these insights, it may appear less surprising that allegedly “irrational” behavior can regularly be produced in experimental settings that expose subjects to standardized reasoning tasks.
4
Content available Strictly associated models, prime basis factorials: an application
100%
Carvalho F.
Discussiones Mathematicae Probability and Statistics
|
2011
|
tom 31
|
nr 1-2
77-86
EN
Mixed models will be considered using the Commutative Jordan Algebra of Symmetric matrices approach. Prime basis factorial models will now be considered in the framework provided by Commutative Jordan Algebra of Symmetric matrices. This will enable to obtain fractional replicates when the number of levels is neither a prime or a power of a prime. We present an application to the effect of lidocaine, at an enzymatic level, on the heart muscle of beagle dogs
5
Content available Second order inferencje in natural language semantics
88%
Pulman S.
Journal of Language Modelling
|
2018
|
tom Vol. 6, No. 1
1--40
EN
In this paper I look at a number of apparently trivial valid inferences (as well as some invalid and missing inferences) associated with the possessive construction and with different types of adjectival modification of nouns. In the case of possessives, all analyses I know of, whether implemented or not, systematically sanction invalid inferences. In the case of adjectives, there are some model-theoretic linguistic analyses that are adequate at a theoretical level, but no satisfactory practical computational implementations that I am aware of which capture the correct inference patterns. A common thread between the possessive and the adjectival construction is that to derive the correct inferences we need secondo order quantification. This is an uncontroversial move within modeltheoretic formal semantics but a problem for computational semantics, since we have no fully automated theorem provers for anything Rother than first order logic (and only for subsets of first order logic do we have provers that are both fully decidable and efficient). I explore what is needed to provide a proof-theoretic account of the relevant inference patterns, and suggest some analyses requiring second order axioms. In order to make this a practical computational possibility I go on to propose two techniques for approximating such inferences in a first order setting. The suggested analyses have been fully implemented, and in an appendix I provide a small FraCaS-like corpus of relevant examples, all of which are handled correctly by the implementation.
6
Content available Separating I/O from application logic for rule-based control systems
88%
Wojnicki I.
Decision Making in Manufacturing and Services
|
2011
|
tom Vol. 5, no. 1-2
79-89
EN
One of the main reasons of using a rule-based approach to program control systems is that they can be formally verified. For such systems communication with the environment is often encoded within the knowledge base. Such inclusion may lead to issues with portability, extendibility, maintainability, and interoperability. The paper proposes a four layer architecture to solve these issues. A proof-of-concept RBS, targeted at control systems, and an example case are also given.
7
Content available Copy raising reconsidered
88%
Melnik N.
Journal of Language Modelling
|
2023
|
tom Vol. 11, No. 2
297--341
EN
There is no consensus in the literature regarding the defining characteristics of copy raising (CR), or in other words what determines whether a CR-like expression is CR or not. As a result, existing analyses target different data sets. In this paper, I propose a different approach to these constructions, which takes a functional perspective. I propose to abandon the term copy raising, which is misleading in a number of ways. Instead, I distinguish between perceptual depiction reports and perceptual inference reports and show that the functions which they fulfill are not particular to CR-like constructions, but are in fact more general. Such an approach, I claim, resolves existing conundrums surrounding CR. The analysis is formalized in the framework of Head-driven Phrase Structure Grammar (HPSG) and is inspired by previous accounts of CR in related frameworks such as LFG and SBCG, as well as HPSG analyses. In the spirit of HPSG, the analysis employs type inheritance hierarchies to distinguish between what is shared by the two constructions and what is construction-specific in order to account for alternative realizations of a single lexeme and to ascribe constructional (or extra-lexical) meaning to linguistic elements.
8
Content available Orthogonal models: Algebraic structure and explicit estimators for estimable vectors
88%
Pereira A. , Fonseca M. , Mexia J.
Discussiones Mathematicae Probability and Statistics
|
2015
|
tom 35
|
nr 1-2
29-44
EN
We study the algebraic structure of orthogonal models thus of mixed models whose variance covariance matrices are all positive semi definite, linear combinations of known pairwise orthogonal projection matrices, POOPM, and whose least square estimators, LSE, of estimable vectors are best linear unbiased estimator, BLUE, whatever the variance components, so they are uniformly BLUE, UBLUE. From the results of the algebraic structure we will get explicit expression for the LSE of these models.
9
Content available Rougir / devenir rouge : l’expression linguistique du langage corporel et ce qu’elle laisse inférer dans un genre textuel
87%
Muryn T.
Studia Romanica Posnaniensia
|
2019
|
tom 46
|
nr 1
137-151
EN
The subject of this article is part of research trying to identify in a textual genre lexico-syntactic constructions with generic markers value. The analysis focuses on the linguistic expression of the manifestation of the blushing body in two textual genres: the detective novel and the romance novel. The aspectual value of these constructions may be related to the textual genre in which they appear because it seems to guide the inferential mechanism in the discovery of implicit information.
10
System ekspertowy w kontroli lotów – badania symulacyjne
75%
Simiński R. , Heflik T.
Studia Informatica
|
2011
|
tom Vol. 32, nr 2B
285-299
PL
Niniejszy artykuł prezentuje koncepcję, implementację oraz skrót badań symulacyjnych inteligentnego komponentu dedykowanego do wspomagania procesów decyzyjnych w kontroli lotów. Komponent ten został zrealizowany jako wbudowany system ekspertowy, zawierający regułową bazę wiedzy, wnioskowanie w przód oraz podsystem wyjaśnień. Dla potrzeb badań zostało zrealizowane środowisko symulacyjne. Przedstawiona praca zawiera niezbędne informacje wprowadzające, opis koncepcji, realizacji oraz symulacji.
EN
This paper presents the conception, realization and simulation study of intelligent component dedicated to aiding the decision making process in flight control. This component was implemented as embedded expert system containing rule knowledge base, forward inference engine and explanation module. The simulation environment was implemented for simulations. Presented work contains some necessary background information, description of conception, realization and simulation study of realized software.
11
Content available Neue Perspektiven der DaF-Lesedidaktik: Eine empirische Untersuchung zum Nutzen inferenzieller und grundgrammatischer Strategien
75%
Cosentino G.
Glottodidactica
|
2014
|
tom 41
|
nr 1
73-89
DE
This paper focuses on the reading competence of a foreign language and aims at showing a particular approach to the reading comprehension of German texts. The role of inference and the knowledge of basic grammar while reading is discussed and particular analytical reading strategies are presented as a support to the theoretical questions. Their validity in the process of meaning reconstruction is finally approved by an empirical study.
12
Content available remote Abductive logic programming in allergy diagnosis
75%
Walecki P. , Lasoń W. , Porębski G. , Obtułowicz K.
Bio-Algorithms and Med-Systems
|
2005
|
tom Vol. 1, no. 1/2
57--60
EN
This paper presents an abductive model of diagnosis, which was designed for medical care (diagnosis and treatment) of certain types of allergy. The reasoning is defined to have three forms: deduction, induction and abduction. The American philosopher Charles S. Peirce was the first to notice abduction. It was characterized as the probative adoption of a hypothesis that explains observed facts (results) in accordance with known laws. Abduction, as cognitive operation, creates the framework, which makes it possible to attribute a singular symptom to a disease. The interpretation of symptoms is always abductive. H.R. Fisher said that every medical diagnostic statement functions as an abductive inference. The abductive schema will become a (nomologically-deductive) principle, if the first premise (the result) contains an unexplained surprising fact (perception, observation) - a symptom in medical diagnosis, which is then explained casually as the effect of a cause. The abductive mode of interference involves two steps. In the first step a fact (a "result" in Peirce's terminology) to be explained or understood is presented, as the derived conclusion in classical schema. The second step introduces an available or newly constructed hypothesis (rule/law) by means of which the case is abducted. Knowledge becomes intelligible by way of its abductive incorporation into a coding system (i.e. medical classification) the logic, which the frame forms by means of new facts.
PL
W pracy zaprezentowano model diagnozy lekarskiej bazujący na wnioskowaniu abdukcyjnym. Model ten został zaprojektowany w celu wspomagania diagnozy i terapii w pewnych przypadkach alergii. Rozumowanie jest definiowane przez trzy podstawowe typy wnioskowania: dedukcję, indukcje i abdukcję. Pierwszym, który wyróżnił i opisał wnioskowanie abdukcyjne był amerykański filozof Charles S. Peirce. Scharakteryzował je jako metodę dochodzenia do hipotezy, która najlepiej wyjaśnia ob serwowane fakty w zgodzie ze znanymi prawami. Abdukcja, jako wnioskowanie logiczne tworzy ramy odniesienia dzięki którym możliwe staje się przypisanie pojedynczego objawu do konkretnej jednostki chorobowej. H.R. Fisher stwierdził, że każda opinia diagnostyczna w medycynie bazuje na wnioskowaniu abdukcyjnym. Jeśli początkowa przesłanka zawiera niewyjaśniony zaskakujący fakt - objaw w medycznej diagnozie, który spontanicznie tłumaczy się jako efekt określonej przyczyny, to wtedy wykorzystujemy schemat wnioskowania abdukcyjnego. Abdukcyjny sposób wnioskowania składa się z dwóch etapów. W pierwszym etapie fakt („result" w terminologii Pierce'a), aby został wytłumaczony czy zrozumiany, zostaje potraktowany, jako konkluzja w klasycznym schemacie inferencji. Drugim etapem jest wprowadzenie dostępnych lub na nowo skonstruowanych hipotez (zasad/praw), za pomocą których dany przypadek jest abdukowany. Objawy wyjaśniane są poprzez ich abdukcyjne włączenie w kodujący system (np. klasyfikacja medyczna) logiki, której postać formuje się dzięki nowym faktom.
13
A Relevance-Theoretic Classification of Jokes
75%
Yus F.
Lodz Papers in Pragmatics
|
2008
|
tom 4
|
nr 1
131-157
EN
Relevance Theory pictures communication as an inferential activity that adjusts, in parallel, the explicit content of utterances, the implicated premises and conclusions that can be derived, and the right amount of contextual information needed to obtain them. When applied to jokes, a relevance-theoretic classification may be proposed depending on whether the humorist plays with the audience's inferential activity aimed at an explicit interpretation, with the audience's inference devoted to deriving implications or with their access to the right amount and quality of contextual information needed to obtain relevant interpretations. In this paper three types of jokes are proposed which focus on these aspects. A fourth type is also added, but this time referred to broad contextual assumptions on social or cultural values of society that are targeted by humorists.
14
Content available remote "Majú inú mentalitu." Esencialistické reprezentácie o Gabčíkovských žiadateľoch o azyl
75%
Maur N.
Český lid: etnologický časopis (Český lid: Ethnological journal)
|
2009
|
tom 96
|
nr 3
247-262
EN
In this paper author focuses on mental representation of ethnic and racial groups in Gabčíkovo village in Slovakia. The objective is to show, that to explain ethnic and racial classification, we need to regard two factors. The first one is social interactions. It means the social, cultural, historical and political conditions of social phenomenon. The second is the cognitive processes of the mind: in what ways the human mind operates particular external information. To explain ethnic and racial classification, the author uses the framework of cognitive anthropology, in particular theory of folk sociology.
15
Wybrane zagadnienia realizacji podsystemu ekspertowego w aplikacji internetowej
75%
Simiński R. , Manaj M.
Studia Informatica
|
2015
|
tom Vol. 36, nr 1
131--143
EN
This article describes the study of selected practical issues focused on the constructing expert system module build-in the web application. We describe a conception of knowledge based subsystem, its goal and method of utilization in whole system. We present functionality of knowledge base editor, we explain the reasons of the attributes’ and rules’ extended description usage. Next we present an examples of application proposed extensions during the inference preprocessing and processing stage.
PL
Niniejszy artykuł prezentuje wybrane praktyczne zagadnienia związane z realizacją podsystemu ekspertowego wbudowanego w aplikację internetową. Opisana została koncepcja takiego podsystemu, jego cele oraz metody wykorzystania w aplikacji. Przedstawione zostały funkcje edytora bazy wiedzy, przyczyny wykorzystania rozszerzonego opisu atrybutów i reguł. Następnie przedstawione zostały przykłady wykorzystania tych rozszerzeń podczas przygotowania do wnioskowania oraz jego realizacji.
16
Content available New developments in fuzzy clustering with emphasis on special types of tasks
75%
Viattchenin D. A. , Owsiński J. W. , Kacprzyk J.
Control and Cybernetics
|
2018
|
tom Vol. 47, no. 2
115--130
EN
The paper is devoted to a survey of work done in fuzzy clustering, mainly during the first decade of the 21st century, and that with emphasis on various approachesto the problem, as well as various formulations of the very problem. That is why not only the classical formulations are treated, but several other problems, related to (the use of) clustering, like feature selection, inference systems, three-way clustering, and, on the other hand, such formulations of clustering as the possibilistic one or the one involving intuitionistic fuzzy sets. These are treated as the background for presentation of some specific ideas of the main author, concerning definite heuristic algorithms for effective solving of some of these problems.
17
Biblioteka KBExpertLib dla języka Java – właściwości funkcjonalne i badania wydajnościowe
75%
Simiński R.
Studia Informatica
|
2016
|
tom Vol. 37, nr 1
125--134
PL
Biblioteka KBExpertLib jest nowym, w pełni autorskim pakietem, oprogramowaniem, oferującym większość typowych funkcji jądra szkieletowego systemu ekspertowego Biblioteka pozwala na budowanie systemów ekspertowych z wykorzystaniem języka Java. Celem niniejszej pracy jest prezentacja właściwości funkcjonalnych biblioteki KBExpertLib oraz wyników badań wydajnościowych najistotniejszy operacji przez nią oferowanych. Eksperymenty są skoncentrowane na badaniu wydajności czasowej podstawowych operacji biblioteki oraz ocenie jej wymagań pamięciowych. W trakcie badań wykorzystywane były rzeczywiste bazy wiedzy, w tym licząca ponad 20 000 reguł.
EN
The KBExpertLib is the originally designed software package which provides most of the expert system shell’s common functions. This library allows to build expert systems using Java programming language. The presentation of the functional properties of the KBExpertLib is the goal of this paper as well as the performance study of basic activities provided by the library. The experimental research are focused on the time efficiency of the basic KBExpertLib operations. The estimation of the memory occupation of the library data structures are also presented. The experiment was performed on the real-world knowledge bases, counting more than 20 000 rules.
18
Content available remote Perceptual Judgement in Late Medieval Perspectivist Psychology
75%
Silva J. F.
Filosofický časopis (Philosophical Journal)
|
2017
|
tom 65
|
nr Special Issue 2
29-60
EN
By the end of the thirteenth century several models of visual perception were available in the Latin West, differing according to their influences – Aristotelian, Augustinian, Avicennian – and their interpretations. One such model was that of perspectivist optics, as espoused by Alhacen and popularized by Roger Bacon. While the general structure of this theory is well-known, until recently scholars have paid less attention to the issue of discrimination – distinction, comparison, judgment – by a higher cognitive faculty (the virtus distinctiva) of incoming sensory information. In my paper, I specifically examine what role this discriminative faculty, as proposed by Alhacen, plays in the works of later perspectivi such as Roger Bacon, John Pecham, and Blasius of Parma, proceeding from the assumption that the best way to understanding the influence of any given theory is by understanding the authors influenced by it. My focus is on two aspects of this power: what exactly its functions are, and whether its nature is rational or sensory. Building on this last aspect, I consider whether this nature is better suited for passive or active accounts of perception.
19
Wizualizacja wnioskowania w regułowych bazach wiedzy z wykorzystaniem sieci Petriego
75%
Simiński R. , Janus S.
Studia Informatica
|
2011
|
tom Vol. 32, nr 2A
459-472
PL
Artykuł przedstawia koncepcję wykorzystania sieci Petriego do zadania wizualizacji struktury regułowej bazy wiedzy oraz prezentuje funkcjonalne oraz implementacyjne aspekty systemu, wykorzystującego tę koncepcję do wizualizacji struktury regułowej bazy wiedzy oraz procesu wnioskowania dla takich baz. W artyŹkule przedstawiono podstawowe zagadnienia związane z sieciami Petriego oraz wykorzystanie sieci do modelowania procesów wnioskowania oraz krótki opis realizacji systemu wykorzystującego tę koncepcję modelowania.
EN
The paper presents conception of utilization of Petri nets to visualization the structure of rule knowledge bases and the functional and implementation issues of system using this conception for visualization both the structure of knowledge bases and the inference process in such bases. The basic terms of Petri nets as well as the idea of using Petri nets as the modeling rule knowledge base have been presented in this paper. The methods of using Petri nets for modeling of the inference process has been also discussed in this paper together with description of realization features of proper software.
20
Content available remote Peirceovo chápanie abdukcie z metodologicko-epistemologického hľadiska
75%
Országh L.
Filosofický časopis (Philosophical Journal)
|
2019
|
tom 67
|
nr 1
45-67
EN
The question of the nature of scientific discovery and the attempt to answer it has not so far met with success. One of the approaches taken, introduced by C. S. Peirce, is the model of abduction. This study sets itself two goals. The first goal is to point to the original purpose and understanding of logic and abduction in the mature work of Peirce as a complex of processes whose analysis falls within the area of the metho­dology of science and epistemology rather than within formal logic. The second goal is to present elements of abduction in Peirce’s mature conception of science which have been given less attention than has the analysis of the formal-logical structure of that conception. Relevant here, above all, are the influences of unconscious processes, such as inspiration and instinct, on the creation of explanatory hypotheses, and their place in abduction. On the basis of this analysis we arrive at two conclusions. Firstly, abduction does not fulfill the requirements of the “logic of discovery” that are set out by formal logic. Secondly, Peirce’s historical, progressive approach, the aim of which is to connect the study of mental processes and the logic and theory of science, constitutes a possible alternative to the purely formal approach to the question of scientific discovery.
DE
Die Frage der wissenschaftlichen Entdeckung und die Bemühung um eine Lösung dieser Frage sind bislang nicht von Erfolg gekrönt. Einen Lösungsansatz stellt hier das von Ch. S. Peirce eingeführte Modell der Abduktion dar. Die vorliegende Studie hat zwei Ziele: Erstens den Hinweis auf die ursprüngliche Stoßrichtung und das Verständnis der Logik und der Abduktion beim späten Peirce als ein Komplex von Prozessen, deren Analyse eher in den Bereich der wissenschaftlichen Methodologie und der Epistemologie als in den Bereich der formalen Logik fällt. Das zweite Ziel besteht darin, jene Elemente der Abduktion des Wissenschaftskonzepts beim späten Peirce vorzustellen, denen im Vergleich zur Analyse ihrer formal-logischen Struktur geringere Aufmerksamkeit gewidmet wird. Es handelt sich dabei insbesondere um die Einflüsse unbewusster Prozesse wie beispielweise Inspiration und Instinkt auf die Bildung der erläuternden Hypothese und auf deren Stellung in der Abduktion. Die vorgenommene Analyse bringt dabei zwei Schlussfolgerungen: Erstens erfüllt die Abduktion nicht die Anforderungen an die „Logik der Entdeckung“, so wie sie die formale Logik stellt. Zweitens kann Peirces historisch-fortschrittlicher Ansatz, dessen Ziel die Verbindung des Studiums mentaler Prozesse mit der Logik und der Wissenschaftstheorie ist, eine Alternative zum rein formalen Ansatz bezüglich der Frage der wissenschaftlichen Entdeckung darstellen.
first rewind previous Strona / 3 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.