Search results for "proposition"

showing 10 items of 89 documents

Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization With Medical Applications

2019

Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, for the first time, a text categorization approach that leverages the recently introduced Tsetlin Machine. In all brevity, we represent the terms of a text as propositional variables. From these, we capture categories using simple propositional formulae, such as: if "rash" and "reaction" and "penicillin" then Allergy. The Tsetlin Machine learns these formulae from a labelled tex…

FOS: Computer and information sciencesComputer Science - Machine LearningGeneral Computer ScienceComputer sciencetext categorizationNatural language understandingDecision treeMachine Learning (stat.ML)02 engineering and technologyVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550::Annen informasjonsteknologi: 559Machine learningcomputer.software_genresupervised learningMachine Learning (cs.LG)Naive Bayes classifierText miningStatistics - Machine Learning0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceTsetlin machinehealth informaticsInterpretabilityPropositional variableClassification algorithmsArtificial neural networkbusiness.industryDeep learning020208 electrical & electronic engineeringGeneral EngineeringRandom forestSupport vector machinemachine learningCategorization020201 artificial intelligence & image processingArtificial intelligencelcsh:Electrical engineering. Electronics. Nuclear engineeringbusinessPrecision and recallcomputerlcsh:TK1-9971
researchProduct

On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators

2020

The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct properties, such as interpretability, simplicity, and hardware-friendliness. Although numerous empirical evaluations report on its performance, the mathematical analysis of its convergence is still open. In this article, we analyze the convergence of the TM with only one clause involved for classification. More specifically, we examine two basic logical operators, namely, the "IDENTITY"- and "NOT" operators. Our analysis reveals that the TM, with just one clause, can converge correctly to the intended logical operator, learning from training data over an infinite time horizon. Besides, it can capture arbit…

FOS: Computer and information sciencesComputer Science - Machine LearningTraining setLearning automataComputer Science - Artificial IntelligenceComputer sciencebusiness.industryApplied MathematicsTime horizonPropositional calculusLogical connectiveMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Operator (computer programming)Computational Theory and MathematicsArtificial IntelligencePattern recognition (psychology)Convergence (routing)Identity (object-oriented programming)Computer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareInterpretabilityIEEE Transactions on Pattern Analysis and Machine Intelligence
researchProduct

Inferences are just folk psychology

2004

To speak of “inferences,” “interpretations,” and so forth is just folk psychology. It creates new homunculi, and it is also implausible from a purely phenomenological perspective. Phenomenal volition must be described in the conceptual framework of an empirically plausible theory of mental representation. It is a non sequitur to conclude from dissociability that the functional properties determining phenomenal volition never make a causal contribution. I have offered an alternative interpretation of some of Dan Wegner’s most relevant data elsewhere (Metzinger 2003, p. 506ff), and will confine myself to three conceptual points here. Wegner’s project could be further strengthened by eliminati…

FallacyPhysiologymedia_common.quotation_subjectState of affairsPropositionBehavioral NeuroscienceNeuropsychology and Physiological PsychologyFolk psychologyMental representationIntrospectionNon sequiturCausationPsychologymedia_commonCognitive psychologyBehavioral and Brain Sciences
researchProduct

An extension of the algebra of sets

1973

We shall explain the aim which leads us in the construction of an extended system of the algebra of sets1. The symbol 1. {*:?(*)} denoting the set of these and only these elements of domain of the variable x which satisfy the propositional condition (propositional function or form) ?9 (x)" is in com? mon use nowadays, so that it is adopted in school courses of mathematics in many countries, and in Poland as well. This condition will be said to define the set 1. However, if we admit propositional conditions which are meaningless for some values of their variables then we encounter some difficulties connected with the ex? pression 1. The formulae 2. {x : 9 (*)} = {x : 9 (*)}' 3. {x : 9 (s) v …

Filtered algebraDiscrete mathematicsHistory and Philosophy of SciencePropositional functionQuaternion algebraLogicIncidence algebraAlgebra of setsTwo-element Boolean algebraNormal extensionField of setsMathematicsStudia Logica
researchProduct

La situation actuelle de la protection du droit à la terre de las communautés 'quilombolas' et futurs défis

2016

Resumo: A construção da nação brasileira atravessou o período da escravidão, que, ao desaparecer, não incluiu o negro de maneira efetiva na sociedade. Desde o final do século XX, as reivindicações desses grupos se tornaram frequentes, gerando uma política compensatória, refletida no contexto legislativo. Nesse sentido, o objetivo deste artigo é examinar a efetividade do direito das comunidades quilombolas aos títulos das terras por elas habitadas. Para isso, a proposta de Emenda Constitucional 215/2000 será analisada. Abstract: The construction of the Brazilian nation went through the period of slavery. Once it was abolished, black people were not included effectively in society. Since the …

H1-99derechos sobre la tierradireito à terraright to landdroits fonciersproposition d'amendement constitutionnel 215/2000communautés quilombolasSocial sciences (General)proposta de emenda constitucional 215/2000comunidades quilombolasPolitical scienceproposed constitutional amendment 215/2000Current (fluid)quilombo communitiesEnvironmental planningpropuesta de enmienda constitucional 215/2000
researchProduct

On the relation between present and future tense in Lithuanian: Preliminary considerations in the domain of non-deictic tense use

2021

The article examines non-deictic uses of present and future tense in Lithuanian. Narrative use, in which reference intervals match with singular events, is distinguished from suspended propositions characterized by lack of such reference intervals (habitual, dispositional and circumstantial modal, and conditional meanings). Present tense is frequently involved in both usage domains, while the future is rare in narrative use, but overlaps with present tense in certain types of suspended propositions. Moreover, its temporal-deictic use is inherently associated with suspended propositions and “linked” to them via epistemic implicatures. This, in contrast to the present, makes the future more l…

H1-99nonpast-domainPhilosophy. Psychology. Religionnarrative presentSlavicPresent tenseP1-1091LithuanianDeixisCircumstantial evidencelanguage.human_languageLinguisticsnon-deictic tense useSocial sciences (General)Future tenseFeature (linguistics)LithuanianBlanguagesuspended propositionsNarrativeSlavic languagesPsychologyPhilology. LinguisticsVilnius University Open Series
researchProduct

From Arithmetic to Logic based AI: A Comparative Analysis of Neural Networks and Tsetlin Machine

2020

Neural networks constitute a well-established design method for current and future generations of artificial intelligence. They depends on regressed arithmetic between perceptrons organized in multiple layers to derive a set of weights that can be used for classification or prediction. Over the past few decades, significant progress has been made in low-complexity designs enabled by powerful hardware/software ecosystems. Built on the foundations of finite-state automata and game theory, Tsetlin Machine is increasingly gaining momentum as an emerging artificial intelligence design method. It is fundamentally based on propositional logic based formulation using booleanized input features. Rec…

Hardware architectureArtificial neural networkLearning automataComputer science020208 electrical & electronic engineering02 engineering and technologyEnergy consumptionPerceptronPropositional calculus020202 computer hardware & architectureAutomaton0202 electrical engineering electronic engineering information engineeringArithmeticEfficient energy use2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
researchProduct

A Tsetlin Machine with Multigranular Clauses

2019

The recently introduced Tsetlin Machine (TM) has provided competitive pattern recognition accuracy in several benchmarks, however, requires a 3-dimensional hyperparameter search. In this paper, we introduce the Multigranular Tsetlin Machine (MTM). The MTM eliminates the specificity hyperparameter, used by the TM to control the granularity of the conjunctive clauses that it produces for recognizing patterns. Instead of using a fixed global specificity, we encode varying specificity as part of the clauses, rendering the clauses multigranular. This makes it easier to configure the TM because the dimensionality of the hyperparameter search space is reduced to only two dimensions. Indeed, it tur…

HyperparameterLearning automataComputer sciencebusiness.industrySupervised learningPattern recognitionGranularityArtificial intelligenceENCODEPropositional calculusbusinessRendering (computer graphics)Curse of dimensionality
researchProduct

Measuring the Novelty of Natural Language Text Using the Conjunctive Clauses of a Tsetlin Machine Text Classifier

2020

Most supervised text classification approaches assume a closed world, counting on all classes being present in the data at training time. This assumption can lead to unpredictable behaviour during operation, whenever novel, previously unseen, classes appear. Although deep learning-based methods have recently been used for novelty detection, they are challenging to interpret due to their black-box nature. This paper addresses \emph{interpretable} open-world text classification, where the trained classifier must deal with novel classes during operation. To this end, we extend the recently introduced Tsetlin machine (TM) with a novelty scoring mechanism. The mechanism uses the conjunctive clau…

I.2FOS: Computer and information sciencesComputer Science - Machine LearningI.5Computer Science - Artificial IntelligenceComputer scienceI.2; I.5; I.7computer.software_genreI.7Novelty detectionMeasure (mathematics)Machine Learning (cs.LG)Representation (mathematics)Computer Science - Computation and Languagebusiness.industryDeep learningNoveltyPropositional calculusArtificial Intelligence (cs.AI)Artificial intelligencebusinessClassifier (UML)computerComputation and Language (cs.CL)Natural language processingNatural language
researchProduct

How store design contributes to the evolution of retail brand positioning : a longitudinal case study

2014

One of the innovative ways favoured by retailers to drive change in their value proposition is to review the design of their stores. Academic contributions to the in-store experience have mostly focused on consumer perspective and identifying relevant managerial practices. The core of this research studies how repositioning a retail brand translates into the experiential design of retail spaces. To this end, the research follows the repositioning process from a managerial perspective and updates the mechanisms that underlie it. The longitudinal study of embedded cases reveals the importance of an holistic design that takes into account the desired interactions between the shopper and the st…

In-store experienceStore designValue propositionDesign de l’espace de venteLongitudinal study of embedded casesÉtude longitudinale de cas enchâssésBrand store (re)positioningCo-création de valeurCo-creation of valueProposition de valeur(re)positionnement de l’enseigneExpérience en magasinGestion du commerce de détail[SHS.GESTION] Humanities and Social Sciences/Business administrationRetailing management
researchProduct