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

Permanent URI for this collection

https://repositorio.uai.edu.ar/handle/123456789/301

Browse

Recent Submissions

Now showing 1 - 5 of 20
  • Item
    A baseline underwater soundscape of an intensely human-exploited estuarine and the effects of vessel traffic sound
    (Sociedad Argentina de Informática e Investigación Operativa (SADIO), 2024-8-28) Pons, Juan ; Uibrig, Román ; Molina, Juan ; Pons, Claudia Fabiana
    In this article we studied the anthropically impacted natural environ mental sound in the port of Bahía Blanca, located in the southern province of Buenos Aires, Argentina. To acquire the acoustic signals, an omni-directional passive hydrophone was used. The acoustic signals were analysed using scripts implemented in the R programming language. Temporal series without maritime traffic were used as a baseline to describe the soundscape in the harbour area by estimating its power spectral density (PSD). Subsequently, the acoustic environ ment was analysed with the presence of two man-made acoustic sources “boat” and “ship” in the vicinity. Finally, the calculated normal soundscape level in the harbour has a magnitude of 116.25 dB re 1 µPa.
  • Item
    El desafío de Scrum distribuido en diferentes locaciones
    (Sociedad Argentina de Informática (SADIO), 2023-10-12) Pons, Claudia Fabiana ; Salazar, Joaquin ; Grimaldi, Pablo
    En las últimas décadas la tecnología ha avanzado rápidamente y con ella la forma de trabajo de todas las personas relacionadas con IT, hoy en día es totalmente normal que un equipo esté integrado por personas que están en diferentes ciudades del mundo, trabajando de manera remota o con diferentes husos horarios e idiomas. Al mismo tiempo, el uso de las metodologías ágiles; principalmente Scrum, ha tenido un gran crecimiento en su implementación. Por esta razón es oportuno poder realizar un análisis de todos los desafíos que implica usar Scrum de manera distribuida, brindando además un aporte de posibles soluciones y consejos para afrontarlos.
  • Item
    Rule Extraction in Trained Feedforward Deep Neural Networks: Integrating Cosine Similarity and Logic for Explainability
    (IGI Global Scientific Publishing, 2024-8-5) Negro, Pablo Ariel ; Pons, Claudia Fabiana
    Explainability is a key aspect of machine learning, necessary for ensuring transparency and trust in decision-making processes. As machine learning models become more complex, the integration of neural and symbolic approaches has emerged as a promising solution to the explainability problem. One effective solution involves using search techniques to extract rules from trained deep neural networks by examining weight and bias values and calculating their correlation with outputs. This article proposes incorporating cosine similarity in this process to narrow down the search space and identify the critical path connecting inputs to final results. Additionally, the integration of first-order logic (FOL) is suggested to provide a more comprehensive and interpretable understanding of the decision-making process. By leveraging cosine similarity and FOL, an innovative algorithm capable of extracting and explaining rule patterns learned by a feedforward trained neural network was developed and tested in two use cases, demonstrating its effectiveness in providing insights into model behavior.
  • Item
    Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
    (Editora SETREM, 2023-10-7) Pons, Claudia Fabiana ; Pérez, Gabriela ; Jacinto, Milagros ; Moschettoni, Martín
    This paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.
  • Item
    Identificación de propiedades biológicas en organismos utilizando técnicas de Machine Learning sobre secuencias de genoma completo
    (Sociedad Argentina de Informática (SADIO), 2023-10-12) Pons, Claudia Fabiana ; Ferella, Nicolás ; Pizio, Pablo Román
    El avance de la tecnología y los procesos de secuenciación de genomas de las últimas décadas ha logrado poner al alcance de investigadores de todo el mundo grandes volúmenes de datos biológicos, que debido a su gran escala, los mismos resultan difíciles de analizar en su totalidad, por lo cual es intuitivo pensar en Inteligencia Artificial para trabajar con dicha información. Con el objetivo de disminuir la brecha existente entre el investigador y las herramientas de Inteligencia Artificial, se desarrolló un software que permite crear un espacio de trabajo para un organismo biológico, realizar el procesamiento de los genomas correspondientes y permitir la creación y entrenamiento de modelos de Machine Learning desde una interfaz gráfica. Los modelos entrenados luego se analizan para buscar qué patrones determinan el resultado de la propiedad biológica a investigar sobre el organismo biológico en cuestión, y así encontrar los genes de mayor impacto en las predicciones del modelo, permitiendo al investigador el posterior análisis en laboratorio de un gen deseado.