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 23
  • Item
    A Co-Training Model Based in Learning Transfer for the Classification of Research Papers
    (IEEE, 2024-10-9) Cevallos Culqui, Alex ; Pons, Claudia Fabiana ; Rodríguez, Gustavo
    A multitude of scholarly papers can be accessed online, and their continual growth poses challenges in categorization. In diverse academic fields, organizing these documents is important, as it assists institutions, journals, and scholars in structuring their content to improve the visibility of research. In this study, we propose a co-training model based on transfer learning to classify papers according to institutional research lines. We utilize cotraining text processing techniques to enhance model learning through transformers, enabling the identification of trends and patterns in document texts. The model is structured with two views (titles and abstracts) for data preprocessing and training. Each input employs different document representation techniques that augment its training using BERT's pre-trained scheme. For evaluating the proposed model, a dataset comprising 898 institutional papers is compiled. These documents undergo classification prediction in five or eleven classes, and the model performance is compared with individually trained models from each view using the BART pre-trained scheme and combined models. The best precision level of 0,87 has been achieved, compared to BERT pre-trained model's metric of 0,78 (five classes). These findings suggest that co-training models can be a valuable approach to improve the predictive performance of text classification.
  • Item
    Rule Extraction in Trained Feedforward Deep Neural Networks - Integrating Cosine Similarity and Logic for Explainability
    (Universidad Abierta Interamericana. Facultad de Tecnología Informática, 2024-12-30) Negro, Pablo Ariel ; Pons, Claudia Fabiana
    Explainability is a fundamental aspect in the field of machine learning, particularly in ensuring transparency and trust in decision-making processes. As the complexity of machine learning models increases, the integration of neural and symbolic approaches has emerged as a promising solution to the explainability problem. In this context, the utilization of search methods for rule extraction in trained deep neural networks has been proven effective. This involves the examination of weight and bias values generated by the network, typically through calculating the correlation between weight vectors and outputs. The hypothesis developed in this article states that by incorporating cosine similarity in this process, the search space can be efficiently narrowed down to identify the critical path connecting inputs to results. Furthermore, to provide a more comprehensive and interpretable understanding of the decision making process, this article proposes the integration of first-order logic (FOL) in the rule extraction process. By leveraging cosine similarity and FOL, a groundbreaking algorithm that is capable of extracting and explaining the rule patterns learned by a feedforward trained neural network was designed and implemented. The algorithm was tested in three use cases showing effectiveness in providing insights into the model’s behavior.
  • 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
    Extracción de reglas de redes neuronales feedforward entrenadas con lógica de primer orden
    (Sociedad Argentina de Informática e Investigación Operativa (SADIO), 2024-4-18) Negro, Pablo Ariel ; Pons, Claudia Fabiana
    La necesidad de integración neural-simbólica se hace evidente a medida que se abordan problemas más complejos, y que van más allá de tareas de dominio limitadas como lo es la clasificación. Los métodos de búsqueda para la extracción de reglas de las redes neuronales funcionan enviando combinaciones de datos de entrada que activan un conjunto de neuronas. Ordenando adecuadamente los pesos de entrada de una neurona, es posible acotar el espacio de búsqueda. Con base en esta observación, este trabajo tiene por objetivo presentar un método para extraer el patrón de reglas aprendido por una red neuronal entrenada feedforward, analizar sus propiedades y explicar estos patrones a través del uso de lógica de primer orden (FOL).
  • 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.