Técnicas de Inteligencia Artificial basadas en una integración de la lógica simbólica y no-simbólica

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 10
  • Item
    Model-Driven Development of Groupware Systems
    (IGI Global, 2022) Pons, Claudia Fabiana ; Bibbo, Luis Mariano ; Giandini, Roxana
    Building Collaborative systems with awareness (or groupware) is a very complex task. This article presents the use of the domain specific language CSSL v2.0 - Collaborative Software System Language -built as an extension of UML, using the metamodeling mechanism. CSSL provides simplicity, expressiveness and precision to model the main concepts of collaborative systems, especially collaborative processes, protocols and awareness. The CSSL concrete syntax is defined via a set of editors through which collaborative systems models are created. According to the MDD methodology, models are independent of the implementation platform and are formally prepared to be transformed. The target of the transformation is a web application that provides a set of basic functions that developers can refine to complete the development of the collaborative system. Finally, evaluation, validation and verification of the language is performed, determining that the CSSL tools allow developers to solve central aspects of collaborative systems implementation in a simple and reasonable way.
  • Item
    Arquitectura para sustentar la integración de conocimiento externo heterogéneo en un motor de reglas
    (Studies Publicações, 2022-6) Maciel, Marcos Antonio ; Pons, Claudia Fabiana
    En un contexto de negocios globalizado donde la completitud de la información se obtiene al componer varias partes, resolver problemas se convierte en una tarea que involucra tiempo, análisis y experiencia. Una organización ve limitado su ámbito de acción porque necesita información de terceros para evaluar en forma íntegra y completa una colección de datos. Para superar estos problemas se propone implementar un motor de reglas capaz de interactuar mediante reglas con servicios usando Json como mensajería de intercambio de datos. El modelo propuesto mejora la capacidad de conocimiento al compartir información entre sistemas heterogéneos usando los estándares de la comunidad para resolver problemas complejos.
  • Item
    La nueva inteligencia artificial : conceptos básicos y aplicaciones
    (Asociación Química Argentina, 2022-8) Pons, Claudia Fabiana ; Pérez, Gabriela ; Baum, Gabriel
    En este artículo se explican los conceptos teóricos y las nociones intuitivas que conforman a la nueva Inteligencia Artificial, en especial al Aprendizaje de Máquina basado en Redes Neuronales Artificiales. Se recorren sus orígenes y fundamentos. Se describen sus principales aplicaciones y herramientas técnicas. Finalmente se comparten reflexiones acerca de las tendencias tecnológicas en el área y se presentan experiencias de aplicaciones desarrolladas en grupos de investigación de la Universidad Nacional de La Plata.
  • Item
    ¿Qué factores personales afectan a la calidad y productividad de TDD? : un experimento con profesionales
    (Sociedad Argentina de Informática, SADIO, 2022-7-21) Pons, Claudia Fabiana ; Raura, Geovanny ; Fonseca, Efraín R. ; Dieste, Oscar
    Test-Driven Development (TDD) es una técnica de desarrollo de software ágil que es ampliamente utilizada en la indus- tria, aunque su efectividad ha generado incertidumbre si se compara con técnicas de desarrollo tradicional. Objetivo: Estudiar la efectividad de TDD considerando el grado de influencia de distintos factores humanos. Metodología: Experimento aleatorizado (cross-over 2x2) realizado con sujetos profesionales en un ámbito académico. Resultados: La calidad y productividad al aplicar TDD es algo superior a lo obtenido con el desarrollo iterativo incremental (ITLD). La edad de los participantes, la función que desempeñaban en su trabajo y el conocimiento previo de la técnica de TDD ejercen influencia sobre las variables respuesta.
  • Item
    Artificial Intelligence techniques based on the integration of symbolic logic and deep neural networks : a systematic review of the literature
    (Iberoamerican Society of Artificial Intelligence (IBERAMIA), 2022-6) Negro, Pablo Ariel ; Pons, Claudia Fabiana
    Artificial Intelligence is tackled from two predominant but very different approaches: symbolic Artificial Intelligence, which is inspired by mathematical logic and is based on the manipulation of abstract linguistic representations, and non-symbolic Artificial Intelligence, which focuses on the construction of predictive mathematical models from large sample data sets. Significantly, the shortcomings of each of these approaches align with the strengths of the other, suggesting that an integration between them would be beneficial. A successful synthesis of symbolic and non-symbolic artificial intelligence would give us the advantages of both worlds. This work aims to identify and classify solutions and architectures that use applied Artificial Intelligence techniques, based on the integration of symbolic and non-symbolic logic (particularly machine learning with artificial neural networks), to provide a comprehensive, exhaustive and organized vision of the solutions available in the literature, making them the subject of a carefully designed and implemented SLR (Systematic Literature Review). The resulting technologies are discussed and evaluated from both perspectives: symbolic and non-symbolic Artificial Intelligence. The PICOC method (Population, Intervention, Comparison, Outputs, Context) plus Limits, which determine the scope of the search, has been used to define the research questions and analyze the results. From a total of 65 candidate studies found, 24 articles (37%) relevant to this study were selected. Each study also focuses on different application domains such as intelligent agents, image classification, theorem provers, cyber-security, image interpretation, mathematics, medicine, robotics and general application. Through the analysis of the selected works, it was possible to classify, organize and explain the different ways in which the deficiencies of non-symbolic Artificial Intelligence are addressed by proposals based on symbolic logic. The study also determined in which stages of the development process said proposals are applied. In addition, the study made it possible to determine which are the logic tools that are preferably applied, for each area and each domain. Although no clear architectural pattern has been found, efforts to find a general-purpose model that combines both worlds are driving trends and research efforts.