631 |
Couverture d'un mot bidimensionnel par un motif chevauchant / Covering a bidimensional word with an overlapping patternGamard, Guilhem 30 June 2017 (has links)
Nous étudions dans cette thèse la notion de quasipériodicité,introduite par Apostolico et Ehrenfeucht au début des années 1990,puis étendue aux mots infinis par Solomon Marcus au début des années2000. Un mot (fini ou infini) w est quasipériodique s'il peut êtrecouvert par des occurrences, éventuellement chevauchantes, d'un autremot, fini, appelé sa quasipériode. En 2006, Monteil etMarcus ont introduit la notion plus forte de quasipériodicitémulti-échelles : le fait d'avoir une infinité de quasipériodes.Dans un premier temps, nous étudions la quasipériodicité des motsinfinis bidimensionnels. Nous montrons que, contrairement au casunidimensionnel où la quasipériodicité ne force aucune propriété fortedes mots infinis, il existe des quasipériodes q qui forcent les mots2D q-quasipériodiques à être d'entropie nulle. Nous montrons égalementque la quasipériodicité multi-échelles en deux dimensions forcel'existence de fréquences uniformes pour les facteurs.Dans un deuxième temps, nous donnons des résultats sur les motsinfinis en une dimension. Nous donnons notament une approchepermettant de déterminer les quasipériodes d'un mot infini à partir deses facteurs carrés et de ses facteurs spéciaux. Nous montrons ensuiteque la famille des mots périodiques, ainsi que celle des mots standardsturmiens, peuvent être caractérisées en termes de quasipériodicitémulti-échelles. / We study the notion of quasiperiodicity, introduced by Apostolico and Ehrenfeucht at the beginning of the 1990's, then extended to infinite words by Solomon Marcus at the beginning of the 2000's. A (finite or infinite) word w is quasiperiodic if it can be covered by occurrences, possibly overlapping, of another finite word, call its quasiperiod. In 2006, Monteil and Marcus introduced a stronger notion: multi-scale quasiperiodicity, the property of having infinitely many quasiperiods.First we study quasiperiodicity of two-dimensional infinite words. We show that, by contrast with the one-dimensional case where quasiperiodicity do not force any property on infinite words, there exist quasiperiods q which force 2D q-quasiperiodic words to have zero entropy. We also show that multi-scale quasiperiodicity in two dimension force the existence of uniform frequencies for factors.Then we give results on infinite words in one dimension. Most notably we give a method to determine the quasiperiods of an infinite words from its square and special factors. We show that the family of periodic words and standard Sturmian words are characterizable in terms of multi-scale quasiperiodicity.
|
632 |
Graphical preference representation under a possibilistic framework / Représentation graphique des préférences dans le cadre de la théorie de possibilitésGouider, Héla 30 October 2017 (has links)
La modélisation structurée de préférences, fondée sur les notions d'indépendance préférentielle, a un potentiel énorme pour fournir des approches efficaces pour la représentation et le raisonnement sur les préférences des décideurs dans les applications de la vie réelle. Cette thèse soulève la question de la représentation des préférences par une structure graphique. Nous proposons une nouvelle lecture de réseaux possibilistes, que nous appelons p-pref nets, où les degrés de possibilité représentent des degrés de satisfaction. L'approche utilise des poids de possibilité non instanciés (appelés poids symboliques), pour définir les tables de préférences conditionnelles. Ces tables donnent naissance à des vecteurs de poids symboliques qui codent les préférences qui sont satisfaites et celles qui sont violées dans un contexte donné. Nous nous concentrons ensuite sur les aspects théoriques de la manipulation de ces vecteurs. En effet, la comparaison de ces vecteurs peut s'appuyer sur différentes méthodes: celles induites par la règle de chaînage basée sur le produit ou celle basée sur le minimum que sous-tend le réseau possibiliste, les raffinements du minimum le discrimin, ou leximin, ainsi que l'ordre Pareto, et le Pareto symétrique qui le raffine. Nous prouvons que la comparaison par produit correspond exactement au celle du Pareto symétrique et nous nous concentrons sur les avantages de ce dernier par rapport aux autres méthodes. En outre, nous montrons que l'ordre du produit est consistant avec celui obtenu en comparant des ensembles de préférences satisfaites des tables. L'image est complétée par la proposition des algorithmes d'optimisation et de dominance pour les p-pref nets. Dans ce travail, nous discutons divers outils graphiques pour la représentation des préférences. Nous nous focalisons en particulier sur les CP-nets car ils partagent la même structure graphique que les p-pref nets et sont basés sur la même nature de préférences. Nous prouvons que les ordres induits par les CP-nets ne peuvent pas contredire ceux des p-pref nets et nous avons fixé les contraintes nécessaires pour raffiner les ordres des p-pref nets afin de capturer les contraintes Ceteris Paribus des CP-nets. Cela indique que les CP-nets représentent potentiellement une sous-classe des p-pref nets avec des contraintes. Ensuite, nous fournissons une comparaison approfondie entre les différents modèles graphiques qualitatifs et quantitatifs, et les p-pref nets. Nous en déduisons que ces derniers peuvent être placés à mi- chemin entre les modèles qualitatifs et les modèles quantitatifs puisqu'ils ne nécessitent pas une instanciation complète des poids symboliques alors que des informations supplémentaires sur l'importance des poids peuvent être prises en compte. La dernière partie de ce travail est consacrée à l'extension du modèle proposé pour représenter les préférences de plusieurs agents. Dans un premier temps, nous proposons l'utilisation de réseaux possibilistes où les préférences sont de type tout ou rien et nous définissons le conditionnement dans le cas de distributions booléennes. Nous montrons par ailleurs que ces réseaux multi-agents ont une contrepartie logique utile pour vérifier la cohérence des agents. Nous expliquons les étapes principales pour transformer ces réseaux en format logique. Enfin, nous décrivons une extension pour représenter des préférences nuancées et fournissons des algorithmes pour les requêtes d'optimisation et de dominance. / Structured modeling of preference statements, grounded in the notions of preferential independence, has tremendous potential to provide efficient approaches for modeling and reasoning about decision maker preferences in real-life applications. This thesis raises the question of representing preferences through a graphical structure. We propose a new reading of possibilistic networks, that we call p-pref nets, where possibility weights represent satisfaction degrees. The approach uses non-instantiated possibility weights, which we call symbolic weights, to define conditional preference tables. These conditional preference tables give birth to vectors of symbolic weights that reflect the preferences that are satisfied and those that are violated in a considered situation. We then focus on the theoretical aspects of handling of these vectors. Indeed, the comparison of such vectors may rely on different orderings: the ones induced by the product-based, or the minimum based chain rule underlying the possibilistic network, the discrimin, or leximin refinements of the minimum- based ordering, as well as Pareto ordering, and the symmetric Pareto ordering that refines it. We prove that the product-based comparison corresponds exactly to symmetric Pareto and we focus on its assets compared to the other ordering methods. Besides, we show that productbased ordering is consistent with the ordering obtained by comparing sets of satisfied preference tables. The picture is then completed by the proposition of algorithms for handling optimization and dominance queries. In this work we discuss various graphical tools for preference representation. We shed light particularly on CP-nets since they share the same graphical structure as p-pref nets and are based on the same preference statements. We prove that the CP-net orderings cannot contradict those of the p-pref nets and we found suitable additional constraints to refine p-pref net orderings in order to capture Ceteris Paribus constraints of CP-nets. This indicates that CP-nets potentially represent a subclass of p-pref nets with constraints. Finally, we provide an thorough comparison between the different qualitative and quantitative graphical models and p-pref nets. We deduce that the latter can be positioned halfway between qualitative and quantitative models since they do not need a full instantiation of the symbolic weights while additional information about the relative strengths of these weights can be taken into account. The last part of this work is dedicated to extent the proposed model to represent multiple agents preferences. As a first step, we propose the use of possibilistic networks for representing all or nothing multiple agents preferences and define conditioning in the case of Boolean possibilities. These multiple agents networks have a logical counterpart helpful for checking agents consistency. We explain the main steps for transforming multiple agents networks into logical format. Finally, we outline an extension with priority levels of these networks and provide algorithms for handling optimization and dominance queries.
|
633 |
Titta pappa vem som kommer på besök, nu kommer mamma - en kvalitativ studie om kvinnliga familjeförsörjareNooni, Niklas, Sveinsdóttir, Sunna January 2018 (has links)
Since the industrialization, the role of breadwinning has been part of the male gender identity. Even though it today has become more common with female breadwinners, the previous assumption of the man as a breadwinner is still a norm in society. This study examines what this norm breaking means for women and their relationships with their men. The purpose is to study Swedish women's experiences of being a breadwinner, how it affects the relationship and the roles one has in a relationship. Previous research has mainly been focused on objective financial aspects of female breadwinning but there is a lack of women's subjective experiences. This study is based on qualitative interviews with seven Swedish female breadwinners. The study shows that education is fundamental to explaining their role as female breadwinner. It also shows that the women's personal traits and good relationships with their men explains their experiences of being a female breadwinner. / Rollen som familjeförsörjare har sedan industrialiseringen varit en del av den manliga könsidentiteten. Trots att det idag blivit vanligare med kvinnliga familjeförsörjare, är den tidigare föreställningen om mannen som försörjare fortsatt en norm i samhället. I denna studie undersöks vad denna normbrytning betyder för kvinnorna och deras relationer till sina män. Syftet är att studera svenska kvinnors upplevelser av att vara familjeförsörjare, hur det påverkar relationen och de roller man har i en relation. Tidigare forskning har i hög grad fokuserat på objektiva finansiella aspekter av kvinnlig familjeförsörjning där det finns en avsaknad av kvinnors subjektiva upplevelser. Den här studien är baserad på kvalitativa intervjuer med sju svenska kvinnliga familjeförsörjare. Studien visar att utbildning är grundläggande för att förklara deras roll som familjeförsörjare. Studien visar också att kvinnornas personliga egenskaper och goda relationer till sina män förklarar deras upplevelser av att vara familjeförsörjare.
|
634 |
La condamnation symbolique / The symbolic condemnationBrunie, Juliette 05 April 2017 (has links)
Malgré une référence expresse faite à la condamnation symbolique par le législateur, cette notion demeure méconnue en droit français. Pouvant être définie comme une décision rendue par une autorité ayant pouvoir de juridiction prononçant, à l'égard d'un individu ou d'un acte, une sanction morale dépourvue d'incidences matérielles réelles exprimant la reconnaissance de la violation d'un droit ou du Droit imputable à cet individu ou à cet acte, la condamnation symbolique est présente de manière diffuse dans le droit français : droit civil, droit administratif et droit pénal. Si les dommages et intérêts symboliques en sont l'illustration la plus évidente, ils n'en sont pas la seule. Annulations dans l'intérêt de la loi, exemptions légale et judiciaire de peine, admonestation … sont aussi des condamnations symboliques. L'étude de l'ensemble de ces illustrations a permis de constater que toutes les condamnations symboliques ne sont pas guidées par la même logique. Quand certaines peuvent être qualifiées de normatives, d'autres sont recognitives ou mitigatives. / Despite a reference do to the symbolic condemnation by the lawmaker, this notion remains unknown in French law. It can be defined as a decision taken by an authority having jurisidiction power pronouncing, towards a person or an act, a moral sanction without material impact expressing the recognition of a right or rule of law's violation accountable to this person or act, the symbolic condemnation is present diffusely in French law : civil law, administrative law and criminal law. If nominal damages are the more obvious illustration, it's not the only. Cancellations in interest of law, absolute discharge, reprimand… are also symbolic condemnation. The study of all of these illustrations has enabled to notice that all the symbolics condemnation are not guided by the same logical. When some can be qualified as normatives, others are recognitives or mitigatives.
|
635 |
A arte da palhaçaria e a psicanálise / The clownery and the psychoanalysisAmeli Gabriele Batista Fernandes 08 July 2011 (has links)
Ao visualizar uma figura de nariz vermelho, sapatos grandes e roupas coloridas, muitos podem acreditar que estão diante de um palhaço. Entretanto, o referido personagem não se caracteriza pela indumentária, mas sim por assumir-se ridículo e criar a partir disso. Ele não quer se curar de seus defeitos, pelo contrário, quer utilizá-los para produzir riso. Utilizando a psicanálise como instrumento de interpretação, é possível compreender que o palhaço se define por um modo de relação específico com a falta, radicalmente diferente da forma neurótica e sintomática. Por meio do chiste e do humor, ele acolhe o real inquirindo a realidade e demonstrando com o nonsense que todo sentido é parcial. O chiste elucida a estrutura do inconsciente a qual o palhaço sabe ser incurável. O humor possui a capacidade de rejeitar as reivindicações da realidade e efetivar o princípio de prazer, com a grande vantagem de não ultrapassar os limites da saúde mental. Assim, ele transforma as ocasiões traumáticas em oportunidades para a obtenção de prazer, uma vez que no humor o ego se recusa a sofrer rejeitando as reivindicações da realidade. / When people see a figure in colorful clothes, big shoes and wearing a red nose, they may believe they are seeing a clown. However, this character is not defined by his clothes, but by admitting himself ridiculous and being able to create from it. He/she does not want to overcome his/her faults, on the contrary, he/she wants to use them to produce laughter. By using psychoanalysis as an interpretation tool, it is possible to understand that the clown is defined by having a specific type of relationship with the void, radically different from neurotic and symptomatic forms. Through Witz and humor, he/she embraces the real, questioning reality and demonstrating, through nonsense, that all meaning is partial. The Witz elucidates the structure of the unconscious which the clown knows to be incurable. Humor allows people to reject claims for reality and to acknowledge the principle of pleasure without crossing the lines of mental health. Thus, it turns traumatic occasions into opportunities for obtaining pleasure, since, through humor, the ego refuses to suffer and rejects the demands of reality.
|
636 |
ProUni: revolução simbólica na vida dos beneficiários / ProUni: symbolic revolution in beneficiaries livesAlves, Tamyres Gaby [UNESP] 29 March 2016 (has links)
Submitted by Tamyres Gaby Martins Alves null (tamyres.gabyalves@gmail.com) on 2016-04-26T21:04:39Z
No. of bitstreams: 1
dissertação versão final formatada.pdf: 980418 bytes, checksum: 1ce41cfed9c093e0045e557c28a25718 (MD5) / Approved for entry into archive by Felipe Augusto Arakaki (arakaki@reitoria.unesp.br) on 2016-04-28T20:13:09Z (GMT) No. of bitstreams: 1
alvez_tgm_me_arafcl.pdf: 980418 bytes, checksum: 1ce41cfed9c093e0045e557c28a25718 (MD5) / Made available in DSpace on 2016-04-28T20:13:09Z (GMT). No. of bitstreams: 1
alvez_tgm_me_arafcl.pdf: 980418 bytes, checksum: 1ce41cfed9c093e0045e557c28a25718 (MD5)
Previous issue date: 2016-03-29 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Essa dissertação de mestrado teve como objetivo discutir o ProUni (Programa Universidade para Todos), criado durante o governo Luiz Inácio Lula da Silva. Em primeiro lugar, abordamos a discussão sobre quem são os herdeiros legítimos da educação no Brasil e quem são os jovens, até então excluídos, que passam a ser inseridos no ensino superior via Prouni. Para ampliar a discussão, contamos com entrevistas realizadas com bolsistas e ex-bolsistas do ProUni, visando averiguar o argumento de que esses estudantes estão transformando as suas vidas por meio do programa, o que chamamos de revolução simbólica. / This master's thesis aimed to discuss ProUni (“University for All Program”), created during the government of Luiz Inacio Lula da Silva. First, we provoke a discussion about who are the legitimate heirs of education in Brazil and who are young, hitherto excluded, which become embedded in higher education. To broaden the discussion, we have interviews with scholars and alumni ProUni, aiming to determine the hypothesis that these students are transforming their lives through the program, what we call a symbolic revolution.
|
637 |
Aplicação da computação simbólica na resolução de problemas de condução de calor em cilindros vazados com condições de contorno convectivasCorrêa, Valesca Alves [UNESP] 01 1900 (has links) (PDF)
Made available in DSpace on 2014-06-11T19:35:41Z (GMT). No. of bitstreams: 0
Previous issue date: 2007-01Bitstream added on 2014-06-13T18:48:27Z : No. of bitstreams: 1
correa_va_dr_guara.pdf: 949805 bytes, checksum: 5d0ebae9cf9395efc83588da395f5ab9 (MD5) / Universidade Estadual Paulista (UNESP) / Com a evolução dos sistemas de computação simbólica ampliou-se a capacidade de modelagem e análise de problemas provenientes de equações diferenciais. Propõe-se a resolução da equação da condução de calor em regimes permanente e transiente para uma geometria cilíndrica com condições de contorno convectivas de forma analítica e numérica utilizando o software de computação simbólica Maple. Para este propósito serão empregados para a resolução analítica, o método de separação de variáveis e para a resolução numérica, o método das diferenças finitas com o esquema Crank- Nicolson e explícito. Os resultados obtidos das resoluções analíticas e numéricas, para algumas situações avaliadas são comparadas. As vantagens computacionais da utilização do software Maple são apresentadas. / The evolution of symbolic computation systems enlarges the capacity of modeling and analysis of problems by differential equations. The aim is the resolution of the conduction heat equation in unsteady and steady state for the cylindrical geometry with convective boundary conditions with analytical and numerical solutions using the Maple software. To this results will be used the separated variables method and finite differences to numerical solutions with Crank-Nicolson and explicit schemes. The results obtained for numerical and analytical solutions for some situations it will available and compared. The computational advantages of the Maple software are showed too.
|
638 |
Intelligent optimisation of analogue circuits using particle swarm optimisation, genetic programming and genetic foldingUshie, Ogri James January 2016 (has links)
This research presents various intelligent optimisation methods which are: genetic algorithm (GA), particle swarm optimisation (PSO), artificial bee colony algorithm (ABCA), firefly algorithm (FA) and bacterial foraging optimisation (BFO). It attempts to minimise analogue electronic filter and amplifier circuits, taking a cascode amplifier design as a case study, and utilising the above-mentioned intelligent optimisation algorithms with the aim of determining the best among them to be used. Small signal analysis (SSA) conversion of the cascode circuit is performed while mesh analysis is applied to transform the circuit to matrices form. Computer programmes are developed in Matlab using the above mentioned intelligent optimisation algorithms to minimise the cascode amplifier circuit. The objective function is based on input resistance, output resistance, power consumption, gain, upperfrequency band and lower frequency band. The cascode circuit result presented, applied the above-mentioned existing intelligent optimisation algorithms to optimise the same circuit and compared the techniques with the one using Nelder-Mead and the original circuit simulated in PSpice. Four circuit element types (resistors, capacitors, transistors and operational amplifier (op-amp)) are targeted using the optimisation techniques and subsequently compared to the initial circuit. The PSO based optimised result has proven to be best followed by that of GA optimised technique regarding power consumption reduction and frequency response. This work modifies symbolic circuit analysis in Matlab (MSCAM) tool which utilises Netlist from PSpice or from simulation to generate matrices. These matrices are used for optimisation or to compute circuit parameters. The tool is modified to handle both active and passive elements such as inductors, resistors, capacitors, transistors and op-amps. The transistors are transformed into SSA and op-amp use the SSA that is easy to implement in programming. Results are presented to illustrate the potential of the algorithm. Results are compared to PSpice simulation and the approach handled larger matrices dimensions compared to that of existing symbolic circuit analysis in Matlab tool (SCAM). The SCAM formed matrices by adding additional rows and columns due to how the algorithm was developed which takes more computer resources and limit its performance. Next to this, this work attempts to reduce component count in high-pass, low-pass, and all- pass active filters. Also, it uses a lower order filter to realise same results as higher order filter regarding frequency response curve. The optimisers applied are GA, PSO (the best two methods among them) and Nelder-Mead (the worst method) are used subsequently for the filters optimisation. The filters are converted into their SSA while nodal analysis is applied to transform the circuit to matrices form. High-pass, low-pass, and all- pass active filters results are presented to demonstrate the effectiveness of the technique. Results presented have shown that with a computer code, a lower order op-amp filter can be applied to realise the same results as that of a higher order one. Furthermore, PSO can realise the best results regarding frequency response for the three results, followed by GA whereas Nelder- Mead has the worst results. Furthermore, this research introduced genetic folding (GF), MSCAM, and automatically simulated Netlist into existing genetic programming (GP), which is a new contribution in this work, which enhances the development of independent Matlab toolbox for the evolution of passive and active filter circuits. The active filter circuit evolution especially when operational amplifier is involved as a component is of it first kind in circuit evolution. In the work, only one software package is used instead of combining PSpice and Matlab in electronic circuit simulation. This saves the elapsed time for moving the simulation between the two platforms and reduces the cost of subscription. The evolving circuit from GP using Matlab simulation is automatically transformed into a symbolic Netlist also by Matlab simulation. The Netlist is fed into MSCAM; where MSCAM uses it to generate matrices for the simulation. The matrices enhance frequency response analysis of low-pass, high-pass, band-pass, band-stop of active and passive filter circuits. After the circuit evolution using the developed GP, PSO is then applied to optimise some of the circuits. The algorithm is tested with twelve different circuits (five examples of the active filter, four examples of passive filter circuits and three examples of transistor amplifier circuits) and the results presented have shown that the algorithm is efficient regarding design.
|
639 |
Subcultural distinction in East Asian education : the case of high school rock in TaiwanWang, Chi-Chung January 2017 (has links)
What kind of rock culture would grow out of an exam-oriented educational system? In the western rock world, self-learning has been characterized as most popular musicians’ principal learning pattern, closely intertwined with the “DIY” ethos and the counter school culture. This research aims to present a different case, that of the “schooled” rock music in Taiwan. Over the last three decades, rock music in Taiwan has grown in popularity, while Taipei has gradually earned the reputation of being the “Mandarin pop/indie capital.” In its developmental process, a few characteristics are worthy of the attention of both the Sociology of Education and youth cultural studies. Firstly, learning rock instruments in regular high school is the main route for teenagers to gain access to rock culture. Secondly, where elite students tend to devote more time to rock music activities than other students, their musical repertoire is characterized by producing covers of heavy metal tunes instead of song-writing. This thesis will probe the rationale behind this phenomenon by answering the following questions: What can best explain the appeal of heavy rock to Taiwanese elite high school students? Why do they not write their own songs? Drawing upon data collected through a school ethnography, it is revealed that the ways Taiwanese elite high school students participate in musical activities can be best understood to be part of a subcultural milieu marked by the collective pursuit of “dual excellence in both study and play”. In this symbolic space, the demanding technical requirements for acquiring several playing techniques allow rock to become a rankable sphere of activity in which elite students struggle for subcultural superiority according to measurable musical standards. The emphasis on instrumental virtuosity conforms to students’ competitive disposition manufactured through academic exams. With these features, rock music becomes a particular form of subcultural activity which allows elite students to not only resist educational control, but also exert symbolic violence over peers of lower-ranked high schools by showing technical superiority. This thesis extends the CCCS’s subcultural solution to the analysis of “subcultural distinction”. In distinction to the “internal perspective” of Sarah Thornton’s conception of subcultural capital (1995), a more holistic framework is developed to explore the relationship between the wider patterns of social division, young people’s subcultural participation, and the shaping of the value hierarchy both within and outside the subcultural sphere. Further, the thesis explores the educational system’s active role in shaping youth subcultures. I demonstrate how education in Taiwan is institutionally mediated by the exam regime to be a powerful logic of social differentiation, and the ways young people’s subcultural choices are constrained by their educational career advance from high school to university. The study also has important implications for the educational policy making in Taiwan. By looking at how students “play,” I propose a new exploratory route to illuminate the widespread impact of the exam-oriented educational system on students’ creativity and identity formation.
|
640 |
Investigações sobre raciocínio e aprendizagem temporal em modelos conexionistas / Investigations about temporal reasoning and learning in connectionist modelsBorges, Rafael Vergara January 2007 (has links)
A inteligência computacional é considerada por diferentes autores da atualidade como o destino manifesto da Ciência da Computação. A modelagem de diversos aspectos da cognição, tais como aprendizagem e raciocínio, tem sido a motivação para o desenvolvimento dos paradigmas simbólico e conexionista da inteligência artificial e, mais recentemente, para a integração de ambos com o intuito de unificar as vantagens de cada abordagem em um modelo único. Para o desenvolvimento de sistemas inteligentes, bem como para diversas outras áreas da Ciência da Computação, o tempo é considerado como um componente essencial, e a integração de uma dimensão temporal nestes sistemas é fundamental para conseguir uma representação melhor do comportamento cognitivo. Neste trabalho, propomos o SCTL (Sequential Connectionist Temporal Logic), uma abordagem neuro-simbólica para integrar conhecimento temporal, representado na forma de programas em lógica, em redes neurais recorrentes, de forma que a caracterização semântica de ambas representações sejam equivalentes. Além da estratégia para realizar esta conversão entre representações, e da verificação formal da equivalência semântica, também realizamos uma comparação da estratégia proposta com relação a outros sistemas que realizam representação simbólica e temporal em redes neurais. Por outro lado, também descrevemos, de foma algorítmica, o comportamento desejado para as redes neurais geradas, para realizar tanto inferência quanto aprendizagem sob uma ótica temporal. Este comportamento é analisado em diversos experimentos, buscando comprovar o desempenho de nossa abordagem para a modelagem cognitiva considerando diferentes condições e aplicações. / Computational Intelligence is considered, by di erent authors in present days, the manifest destiny of Computer Science. The modelling of di erent aspects of cognition, such as learning and reasoning, has been a motivation for the integrated development of the symbolic and connectionist paradigms of artificial intelligence. More recently, such integration has led to the construction of models catering for integrated learning and reasoning. The integration of a temporal dimension into such systems is a relevant task as it allows for a richer representation of cognitive behaviour features, since time is considered an essential component in intelligent systems development. This work introduces SCTL (Sequential Connectionist Temporal Logic), a neuralsymbolic approach for integrating temporal knowledge, represented as logic programs, into recurrent neural networks. This integration is done in such a way that the semantic characterization of both representations are equivalent. Besides the strategy to achieve translation from one representation to another, and verification of the semantic equivalence, we also compare the proposed approach to other systems that perform symbolic and temporal representation in neural networks. Moreover, we describe the intended behaviour of the generated neural networks, for both temporal inference and learning through an algorithmic approach. Such behaviour is then evaluated by means several experiments, in order to analyse the performance of the model in cognitive modelling under di erent conditions and applications.
|
Page generated in 0.0607 seconds