Publication: Evaluation and development of consciuousness in artificial cognitive systems
Loading...
Identifiers
Publication date
2011-02
Defense date
2011-02-07
Authors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Impact
Export
Abstract
Históricamente el fenómeno de la conciencia humana ha sido en buena medida apartado del debate científico, siendo su estudio relegado casi exclusivamente al ámbito de la filosofía. Sin embargo, durante las últimas tres décadas se ha producido un interés creciente por el problema de la conciencia en diferentes disciplinas como la filosofía de la mente y la psicología cognitiva. Esta tendencia también se ha producido paralelamente en el ámbito multidisciplinar de las neurociencias. De hecho, la aparición de nuevas técnicas de diagnóstico por imagen ha propiciado que actualmente la mayoría de investigadores considere que la conciencia es susceptible de estudio científico. La formulación de nuevas teorías, tanto biológicas como psicológicas, acerca de la producción de la conciencia en los humanos, ha dado lugar a que se retomen algunos de los objetivos originales de la Inteligencia Artificial. Concretamente, se ha empezado a reconocer el campo de la Conciencia Artificial como una disciplina científica seria que se encarga del estudio y la posible construcción de máquinas con diferentes tipos y niveles de conciencia. En el ámbito de la Conciencia Artificial, la presente tesis pretende contribuir al conocimiento científico de la conciencia por medio de dos líneas de investigación relacionadas: la primera consiste en la concepción y aplicación de un método inédito para la medición y caracterización del nivel de desarrollo de la conciencia en un agente artificial, la segunda se basa en una arquitectura cognitiva artificial cuyo diseño se ha inspirado en diversas teorías de la conciencia. La utilización del método de medición propuesto permitirá analizar en detalle cuál es el nivel de desarrollo actual de máquinas conscientes y establecer cuáles son los aspectos que no se ha conseguido explicar o implementar hasta la fecha. Además, la escala propuesta se podrá utilizar como hoja de ruta para identificar cuáles son las habilidades cognitivas cuya implementación es necesaria para construir máquinas que muestren comportamientos equivalentes a los típicamente humanos. La aplicación de la arquitectura cognitiva propuesta como parte fundamental de los sistemas de control autónomo de agentes artificiales permitirá la experimentación con diferentes funciones cognitivas asociadas a la conciencia. Se estudiarán por tanto las interacciones entre diferentes capacidades como la atención, las emociones o la predicción sensorial, intentando descubrir las sinergias que potencialmente dan lugar a comportamientos complejos y adaptativos. Adicionalmente, usando el modelo computacional de conciencia implementado, se aplicará un enfoque de fenomenología sintética, que consiste en el modelado del contenido de la experiencia consciente. Se comparará la experiencia consciente descrita por un ser humano expuesto a ciertos estímulos perceptivos con el contenido explícito que la arquitectura cognitiva es capaz de generar al enfrentarse a los mismos estímulos. Los resultados de estas líneas de investigación proporcionarán información valiosa acerca de la validez de las teorías de la conciencia analizadas y de las diferencias encontradas entre los procesos cognitivos naturales y los generados artificialmente. Asimismo, se explorarán posibles áreas de aplicación práctica de la arquitectura cognitiva implementada, como por ejemplo, la creación de agentes artificiales cuyo comportamiento sea percibido por los usuarios como comportamiento humano. --------------------------------------------------------------------------------------------------------------------------------------------------
Historically human consciousness has been rather excluded from the scientific debates, being philosphy the most important perspective for its study. However, over the last three decades different research disciplines such as philosophy of mind and cognitive psychology have shown a growing interest on the problem of consciousness. This trend has taken place also in the multidisciplinary context of neuroscience. In fact, recent advances in neuroimaging techniques have led most researchers to consider consciousness as a subject for scientific study. The development of new biological and psychological theories on the production of consciousness in humans has revived the original challenges of Artificial Intelligence. Specifically, the field of Machine Consciousness is becoming a rigorous scientific discipline aimed at studying and potentially creating machines with different types and levels of consciousness. In the context of Machine Consciousness, this thesis aims at contributing to the scientific knowledge about consciousness by means of two interrelated research lines: the first one consists of the conception and application of a novel method for the measurement and characterization of the level of development of consciousness of an artificial agent; the second one is based on an artificial cognitive architecture inspired on several theories of consciousness. The application of the proposed measuring technique will permit the detailed analysis of the current level of development of conscious machines and to identify what are the aspects that have not yet been achieved. Furthermore, the proposed scale will be used as a roadmap to identify what are the key cognitive skills that need to be implemented in order to create human-like machines. The application of the proposed cognitive architecture as a fundamental component of the control system of different artificial agents will permit the experimentation with different cognitive functions associated to consciousness. The interaction between different capabilities like attention, emotions or sensory prediction will be analyzed, looking for potential synergies that produce complex and adaptive behaviors. Additionally, using the proposed computational model of consciousness, a synthetic phenomenology approach will be adopted based on the modeling of the contents of conscious experience. The conscious experience reported by a human subject when confronted to certain stimuli will be compared with the explicit content that the cognitive architecture is able to generate when confronted to the same stimuli. The results obtained from these research lines will provide valuable information about the validity of the theories of consciousness that have been analyzed as well as the differences between natural and artificial cognitive processes. Besides, possible areas of application of the proposed cognitive architecture will be explored, such us the creation of artificial agents able to develop believable human-like behaviors.
Historically human consciousness has been rather excluded from the scientific debates, being philosphy the most important perspective for its study. However, over the last three decades different research disciplines such as philosophy of mind and cognitive psychology have shown a growing interest on the problem of consciousness. This trend has taken place also in the multidisciplinary context of neuroscience. In fact, recent advances in neuroimaging techniques have led most researchers to consider consciousness as a subject for scientific study. The development of new biological and psychological theories on the production of consciousness in humans has revived the original challenges of Artificial Intelligence. Specifically, the field of Machine Consciousness is becoming a rigorous scientific discipline aimed at studying and potentially creating machines with different types and levels of consciousness. In the context of Machine Consciousness, this thesis aims at contributing to the scientific knowledge about consciousness by means of two interrelated research lines: the first one consists of the conception and application of a novel method for the measurement and characterization of the level of development of consciousness of an artificial agent; the second one is based on an artificial cognitive architecture inspired on several theories of consciousness. The application of the proposed measuring technique will permit the detailed analysis of the current level of development of conscious machines and to identify what are the aspects that have not yet been achieved. Furthermore, the proposed scale will be used as a roadmap to identify what are the key cognitive skills that need to be implemented in order to create human-like machines. The application of the proposed cognitive architecture as a fundamental component of the control system of different artificial agents will permit the experimentation with different cognitive functions associated to consciousness. The interaction between different capabilities like attention, emotions or sensory prediction will be analyzed, looking for potential synergies that produce complex and adaptive behaviors. Additionally, using the proposed computational model of consciousness, a synthetic phenomenology approach will be adopted based on the modeling of the contents of conscious experience. The conscious experience reported by a human subject when confronted to certain stimuli will be compared with the explicit content that the cognitive architecture is able to generate when confronted to the same stimuli. The results obtained from these research lines will provide valuable information about the validity of the theories of consciousness that have been analyzed as well as the differences between natural and artificial cognitive processes. Besides, possible areas of application of the proposed cognitive architecture will be explored, such us the creation of artificial agents able to develop believable human-like behaviors.
Description
Keywords
Conciencia artificial, Máquinas conscientes, Sistemas cognitivos, Machine consciousness, Cognitive systems