Virtualization and allostatic control for aware virtual agents
OPEN CALL
INTERDISCIPLINARY WORKSHOP
Virtualization and allostatic control for aware virtual agents
14:00 CET, 23 April 2024 | Duration: 2 hours - Online
DESCRIPTION
In this workshop, participants will be introduced to the role of internal needs, such as hunger, thirst, or thermoregulation, in shaping behaviour, cognition and consciousness. Through interactive coding and exercises, a biologically constrained model of the core behaviour system of the brain stem will be developed, controlling an artificial agent to orchestrate self-regulatory behaviours. In addition, a second coding session will introduce methods from deep learning that show how compressed representations of the environment can be built to aid in decision-making and self-regulation.
SCHEDULE
- Introductory talk: Neural basis of self and self-
- Reactive control: Allostatic orchestration of motivated
- Introductory talk: Compressed representations in the mammalian hippocampus and neural
- Adaptive control: Convolutional autoencoders for data
- Putting it all together in Awareness Architectures
SCIENTIFIC COORDINATION
Scientific team of CAVAA (EIC Awareness Inside project: Counterfactual Assessment and Valuation for Awareness Architecture) coordinated by Prof. Paul Verschure, Donders Centre for Neuroscience – Neurophysics, Radboud.
Co-funded by the European Commission. Further info on the CORDIS EU research platform.
LECTURES
Prof. Paul Verschure, (Donders Centre for Neuroscience – Neurophysics, Radboud University)
Oscar Guerrero Rosado (Ph.D. student in Cognitive Robotics, Donders Centre for Neuroscience – Neurophysics, Radboud University)
Adrian F. Amil (Ph.D. student in NeuroAI, Donders Centre for Neuroscience – Neurophysics, Radboud University)
PARTICIPANTS
Researchers (postgraduate); undergraduate students (3rd year or higher) with a background relevant to the topics: Cognitive Sciences, Computational Neurosciences, Cognitive Robotics, Neuro AI, or similar.
REQUIREMENTS
- University degree (or enrollment) in an affiliated field
- Basic level of Python programming
- Access to Google Colab.
- Intermediate proficiency in the English language
- Enthusiasm and interest in the topic and the desire to actively engage during the session
REGISTRATION
Fill out the registration form and upload your CV and short motivation letter HERE before 30.03.2024. Participation is open (free of charge).
Based on their CVs and motivations, selected participants will be informed via mail by 07.04.2024.
RECOMMENDED LITERATURE:
- Verschure, F. (2016). Synthetic consciousness: the distributed adaptive control perspective. Philosophical Transactions of the Royal Society B: Biological Sciences, 371(1701), 20150448
- Rosado, G., Amil, A. F., Freire, I. T., & Verschure, P. F. (2022). Drive competition underlies effective allostatic orchestration. Frontiers in Robotics and AI, 9, 1052998.
- Santos-Pata, D., Amil, A. F., Raikov, I. G., Rennó-Costa, C., Mura, A., Soltesz, I., & Verschure, P. F. (2021). Epistemic autonomy: self-supervised learning in the mammalian hippocampus. Trends in Cognitive Sciences, 25(7), 582-595.
For any inquiries, please contact Oscar Guerrero Rosado at oscar.guerrerorosado@donders.ru.nl