Зміст
Добірка наукової літератури з теми "Intelligence Artificielle incarnée"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Intelligence Artificielle incarnée".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Intelligence Artificielle incarnée"
Betschart, Christof. "L’humain imago Dei et l’intelligence artificielle imago hominis ?" Recherches de Science Religieuse Tome 111, no. 4 (September 27, 2023): 643–59. http://dx.doi.org/10.3917/rsr.234.0643.
Повний текст джерелаLoor, Pierre de, Alain Mille, and Mehdi Réguigne-Khamassi. "Intelligence artificielle : l’apport des paradigmes incarné." Intellectica. Revue de l'Association pour la Recherche Cognitive 64, no. 2 (2015): 27–52. http://dx.doi.org/10.3406/intel.2015.1011.
Повний текст джерелаBaumard, Philippe. "Quand l’intelligence artificielle théorisera les organisations." Revue Française de Gestion 45, no. 285 (November 2019): 135–59. http://dx.doi.org/10.3166/rfg.2020.00409.
Повний текст джерелаLarsonneur, Claire. "Une machine comme moi, ou l’empathie en question." Imaginaires de l'IA 22 (2024). http://dx.doi.org/10.4000/11tfj.
Повний текст джерелаДисертації з теми "Intelligence Artificielle incarnée"
Dutech, Alain. "Apprentissage par Renforcement : Au delà des Processus Décisionnels de Markov (Vers la cognition incarnée)." Habilitation à diriger des recherches, Université Nancy II, 2010. http://tel.archives-ouvertes.fr/tel-00549108.
Повний текст джерелаGillard, Tristan. "Auto-organisation multi-échelle pour l’émergence de comportements sensorimoteurs coordonnés." Electronic Thesis or Diss., Université de Lorraine, 2022. http://www.theses.fr/2022LORR0353.
Повний текст джерелаNon-associative learning is widely observed throughout phylogeny and appears to be fundamental for the adaptation and, thus, the survival of living organisms. This thesis explores adaptation mechanisms inspired by these non-associative learnings. We propose three computational models of habituation, three models of site-specific sensitization and one model of pseudo-conditioning. We develop these models within the framework of the Iterant Deformable Sensorimotor Medium (IDSM), a recently developed abstract model of sensorimotor behavior formation. The characteristics of the presented models are studied and analyzed in light of our long-term goal of investigating new unsupervised learning mechanisms for autonomous artificial agents
L'haridon, Louis. "La douleur et le plaisir dans la boucle motivation-émotion-cognition : les robots en tant qu'outils et que modèles." Electronic Thesis or Diss., CY Cergy Paris Université, 2024. http://www.theses.fr/2024CYUN1342.
Повний текст джерелаIn this thesis, I explore the integration of pain, its perception, its features, and its sensory process into robotic models, focusing on its influence on motivation-based action selection architecture. Drawing inspiration from clinician psychology, neurobiology, and computation neuroscience, I aim to provide a framework with different perspectives to study how bio-inspired pain mechanisms can affect decision-making systems.Pain plays a crucial role in biological systems, influencing behaviors essential to survival and maintaining homeostasis, yet it is often neglected in emotional models. In humans and other animals, pain serves as an adaptive response to noxious stimuli, triggering protective actions that prevent harm and promote recovery. This thesis seeks to improve action selection by incorporating pain and its related features into robots, extending the current understanding of artificial agents and exploring how robots can use pain to modulate behavior, adapt to threats, and optimize survival.Embracing the embodied Artificial Intelligence paradigm and building upon prior work on motivation-based action selection models, this thesis proposes to study different perspectives on pain and its impact on action selection.First, I provide an overview of related work and the state of the art in relevant disciplines.In the initial part of this work, I propose an enhanced motivation-based action selection architecture by introducing an embodied model that enables robots to perceive and respond to noxious stimuli. Using artificial nociceptors, I simulate the sensation of damage in robotic agents and compute the emotional state of pain as an artificial hormone. This model investigates how varying levels of pain perception influence behavioral responses, with results emphasizing the adaptive value of pain modulation in action selection, particularly in extreme or hazardous environments.Next, I introduce an artificial hormonal neuromodulation mechanism featuring a simulated cortisol hormone that modulates the action selection process. This cortisol mechanism incorporates temporal dynamics, resulting in habituation and sensitization processes. I demonstrate how hormonal neuromodulation can lead to emergent behaviors that improve the overall response of robotic agents to environmental variability in extreme scenarios.Additionally, I propose a novel framework for tactile sensing in mobile robotic platforms. This framework computes a nociceptive and mechanoceptive process capable of localizing and classifying noxious and tactile stimuli. In collaboration with Raphaël Bergoin, we send this sensory signal to a spiking neural network, demonstrating the segregation of cortical areas for nociceptive and mechanoceptive signals and learning embodied sensory representations.Finally, I present an integrated action selection architecture that combines these new mechanoceptive and nociceptive sensory processes, behavioral responses, hormonal neuromodulation, and the learning of embodied representations. This architecture is examined in a social context with varying levels of interaction with predators. I highlight the importance of social interaction in learning embodied sensory representations and demonstrate how this cortex-based model improves hormonal management and action selection in dynamic environments.In conclusion, I discuss the results of this research and offer perspectives for future work
Bang, Sanghun. "Development framework for language acquisition based on the embodied cognition : case of problem solving and gesture." Electronic Thesis or Diss., Paris 8, 2021. http://www.theses.fr/2021PA080007.
Повний текст джерелаThe idea of embodied cognition is based on the fact that our brain is not only a living organ which is connected to our body, but also the mode that the body communicates with our environment. The alive and active brain, which interacts with the environment through our living body, has a major impact on our thinking, especially cognitive thinking. This means that our communicative expressions are composed of bodily component following our sensor-motor systems and emotional components which concerns realization of our sensor-motor actions and of planned actions.It is then possible to perceive the language like as essentially metaphorical : using the bodily actions like as the basis of production and of the assignment of meaning. So we can understand the following sentence “You have undoubtedly followed the consequences at the supermarket checkout: prices rise (more) like the body when it climbs, etc