2020/02/02 by Eduardo C. Garrido‐Merchán, Merchán, Eduardo C. Garrido, Martín Molina +1
Computer Science · #Artificial Intelligence (cs.AI) #Computability, Logic, AI Algorithms #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2002.00509
openalex publication_date 2020/02/02 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Recent developments in machine learning have pushed the tasks that machines\ncan do outside the boundaries of what was thought to be possible years ago.\nMethodologies such as deep learning or generative models have achieved complex\ntasks such as generating art pictures or literature automatically. On the other\nhand, symbolic resources have also been developed further and behave well in\nproblems such as the ones proposed by common sense reasoning. Machine\nConsciousness is a field that has been deeply studied and several theories\nbased in the functionalism philosophical theory like the global workspace\ntheory or information integration have been proposed that try to explain the\nariseness of consciousness in machines. In this work, we propose an\narchitecture that may arise consciousness in a machine based in the global\nworkspace theory and in the assumption that consciousness appear in machines\nthat has cognitive processes and exhibit conscious behaviour. This architecture\nis based in processes that use the recent developments in artificial\nintelligence models which output are these correlated activities. For every one\nof the modules of this architecture, we provide detailed explanations of the\nmodels involved and how they communicate with each other to create the\ncognitive architecture.\n