Interpretación y explicación del comportamiento de redes neuronales artificiales

Permanent URI for this collection

https://repositorio.uai.edu.ar/handle/123456789/4687

Browse

Browsing Interpretación y explicación del comportamiento de redes neuronales artificiales by Subject "artificial intelligence"
  • Item
    Artificial Intelligence Applied in Legal Information: A Systematic Mapping Study
    (Facultad de Informática, Universidad Nacional de La Plata, 2025-4-30) D'alotto, Juan Eduardo ; Pons, Claudia Fabiana ; Antonelli, Ruben Leandro
    Advanced technologies, particularly Artificial Intelligence (AI), are transforming how legal professionals handle civil law relationships and daily processes. Legal Information Retrieval (LIR), a significant field within AI, focuses on efficiently identifying and analyzing legal norms and documents relevant to users' specific information needs. This systematic mapping study identifies and synthesizes primary approaches, trends, and advancements in applying AI to LIR. By reviewing recent research, it provides an overview of employed strategies, AI techniques, and emerging areas of focus. Systematic search methods were applied to academic databases, selecting relevant studies published over the past fifteen years. From 3405 initially identified articles, 34 were selected for in-depth analysis after applying inclusion and exclusion criteria. The findings reveal sustained interest in AI techniques for LIR, with a clear trend toward adopting Natural Language Processing (NLP) and machine learning to enhance search relevance, precision, and automation of legal processes. This study emphasizes the potential of AI in the legal domain and highlights the need for continued research to address unique LIR challenges in a rapidly evolving technological landscape.
  • Item
    Explainable Artificial Intelligence: Analysis of Methodologies and Applications
    (Facultad de Informática, Universidad Nacional de La Plata, 2025-10-22) Pezzini, Maria Cecilia ; Pons, Claudia Fabiana
    Explainability is essential in healthcare, finance, and security, where black-box models can undermine trust and decisions. Recent advances in eXplainable Artificial Intelligence (XAI) across structured/tabular data, computer vision, and natural language processing are surveyed. Thirty articles (2022–2024) were selected through a structured search with explicit inclusion criteria, and emerging approaches are compared with established techniques such as LIME and SHAP, alongside rule-, logic-, and ontology-based methods. Methods are organized along key dimensions—post-hoc vs. ante-hoc, model-agnostic vs. model-specific, scope, problem type, input data, and output format—and their effectiveness and applicability are evaluated. The review highlights innovations including spatially explainable architectures (e.g., SAMCNet) and entropy-based logic explanations, and identifies persistent challenges in robustness, cross-domain generalization, and deployment. Overall, findings consolidate the evolving XAI landscape and indicate directions toward reproducible techniques that strengthen transparency, accountability, and user trust in AI systems.