Formal models of mind and action 2401-CS-MF-FMoMA-s2
During the lecture students will gain the knowledge about the use of formal tools in the modelling of mind and action, such as Bayesian Logics and Non-monotonic Logics. Bayesian Logic is used as a tool of formalisation of Predictive Processing in the explanation of the mind, particularly, how representations modify, enrich and change the mind’s content. Non-monotonic logics (NML) shows how to rationalize the behaviour of an organism and how does an organism learn. NML are already used in the architecture of artificial minds, i.e. in software engineering of bots, chat bots and robots, namely there, where it is needed to predict behaviour and to program the appropriate reactions.
|
W cyklu 2022/23Z:
During the lecture students will gain the knowledge about the use of formal tools in the modelling of mind and action, such as Bayesian Logics and Non-monotonic Logics. Bayesian Logic is used as a tool of formalisation of Predictive Processing in the explanation of the mind, particularly, how representations modify, enrich and change the mind’s content. Non-monotonic logics (NML) shows how to rationalize the behaviour of an organism and how does an organism learn. NML are already used in the architecture of artificial minds, i.e. in software engineering of bots, chat bots and robots, namely there, where it is needed to predict behaviour and to program the appropriate reactions. |
W cyklu 2023/24Z:
During the lecture students will gain the knowledge about the use of formal tools in the modelling of mind and action, such as Bayesian Logics and Non-monotonic Logics. Bayesian Logic is used as a tool of formalisation of Predictive Processing in the explanation of the mind, particularly, how representations modify, enrich and change the mind’s content. Non-monotonic logics (NML) shows how to rationalize the behaviour of an organism and how does an organism learn. NML are already used in the architecture of artificial minds, i.e. in software engineering of bots, chat bots and robots, namely there, where it is needed to predict behaviour and to program the appropriate reactions. |
Całkowity nakład pracy studenta
Efekty uczenia się - wiedza
Efekty uczenia się - umiejętności
Efekty uczenia się - kompetencje społeczne
Metody dydaktyczne
Metody dydaktyczne podające
- wykład konwersatoryjny
- wykład informacyjny (konwencjonalny)
Koordynatorzy przedmiotu
Kryteria oceniania
Assessment methods:
- test
criteria:
fail- less than 50%
satisfactory- 50-55%
satisfactory plus- 55-65%
good – 65-75%
good plus- 75-85%
very good- 85-100%
Literatura
1. Chan, L.W., Hexel, R., Wen, L. (2012), Integrating Non-Monotonic Reasoning into High Level Component-Based Modelling Using Behavior Trees, New Trends in Software Methodologies, Tools and Techniques, H. Fujita and R. Revetria (Eds.), IOS Press.
2. Friston K.J., Daunizeau J., Kiebel S.J. (2009) Reinforcement Learning or Active Inference? PLoS ONE 4(7): e6421. https://doi.org/10.1371/journal.pone.0006421
3. Fodor, J.A. (1994), The Elm and the Experts: Mentalese and Its Sematics, MIT Press.
Więcej informacji
Dodatkowe informacje (np. o kalendarzu rejestracji, prowadzących zajęcia, lokalizacji i terminach zajęć) mogą być dostępne w serwisie USOSweb: