Lecturer: Martin Takac
Fields: Artificial Intelligence/Cognitive Science
Content
How do we know that a system – living or artificial – understands something? If it makes sense of its experience and ascribes it meaning – how is this meaning represented within the system? In my course I will start with basic overview of semantic theories and grounded cognition. I will cover grounding of abstract concepts and language syntax, developmental approach to grounding meaning in AI and also analyze modern large-scale language models and semantics in deep neural networks.
Literature
- Barsalou, L.W. (2008). Grounded cognition. Annual Review of Psychology, 59, 617-645.
- Knott, A. & Takac, M. (2021). Roles for Event Representations in Sensorimotor Experience, Memory Formation, and Language Processing. Topics in Cognitive Science 13(1). 187-205.
- Borghi A.M., Barca L., Binkofski F., Tummolini L. (2018) Varieties of abstract concepts: development, use and representation in the brain. Phil. Trans. R. Soc. B, 373: 20170121
- Smith, L. & Gasser, M. (2005). The Development of Embodied Cognition: Six Lessons from Babies. Artificial Life. Vol. 11, Issues 1-2, pp. 13 – 30.
- Zaadnoordijk, L., Besold, T.R. & Cusack, R. (2022). Lessons from infant learning for unsupervised machine learning. Nature Machine Intelligence 4, 510–520.
- Roy, N. et al (2021): From Machine Learning to Robotics: Challenges and
- Opportunities for Embodied Intelligence. https://doi.org/10.48550/arXiv.2110.15245
Lecturer
Martin Takac received his PhD in artificial intelligence from Comenius University in Bratislava where he currently works as associate professor in cognitive science. His research specializes on computational modelling of sense-making and meaning construction. He is also a co-creator of cognitive architecture of BabyX – a virtual infant.
Affiliation: Comenius University in Bratislava
Homepage: http://cogsci.fmph.uniba.sk/~takac/