Course at a Glance
This course will provide an intensive introduction to the emerging field of artificial cognitive systems. Inspired by artificial intelligence, developmental psychology, and cognitive neuroscience, the aim is to build systems that can act on their own to achieve goals
– perceiving their environment, anticipating the need to act, learning from experience, and adapting to changing circumstances
– and interact with other agents, including humans. Instructors
David Vernon david@vernon.eu
Hours and Credits 10 hours (lectures) 3 credits
Synopsis
We begin by examining what is meant by the term cognition
This allows us to develop a working definition of cognition and cognitive systems, one that strikes a balance between being broad enough to do service to the many views that people have on cognition and deep enough to help in the formulation of theories and models. We then survey the different paradigms of cognitive science to establish the full scope of the subject. We follow this with a discussion of cognitive architectures before tackling the key issues: autonomy, embodiment, learning & development, memory & prospection, knowledge & representation, and social cognition.
Tools used:
HardwareNot applicable
Software
Not applicable
Syllabus
The nature of cognition: models, definitions, autonomy, Marr’s levels of abstraction.
Paradigms of cognitive science: cognitivism, emergent systems, and hybrid systems.
Cognitive architectures: cognitivist, emergent, and hybrid architectures, desirable characteristics, example cognitive architectures.
Autonomy: robotic, biological, behavioural, & constitutive autonomy, homeostasis, self- maintenance, continuous reciprocal causation, autonomic systems.
Embodiment: the three hypotheses, the mutual dependence of perception and action, off-line embodied cognition, situated, embedded, grounded, extended, and distributed cognition.
Development and learning: motives, imitation, supervised, unsupervised, and reinforcement learning, phylogeny and ontogeny, developmental psychology.
Memory and prospection: short-term, long-term, declarative, procedural, semantic, episodic, symbolic, sub-symbolic, internal simulation, prospection.
Knowledge and representation: memory and knowledge, representation, anti-
representation, sharing knowledge, radical constructivism, symbol grounding, learning from demonstration.
Social cognition: interaction, intentionality, theory of mind, instrumental helping, collaboration, joint action, shared intention, shared goals, joint attention, development and interaction dynamics.
Final exam
There will be a final examination decided by the instructors.
Prerequisites None.
Reading List
Vernon, D. Artificial Cognitive Systems – A Primer, MIT Press, 2014.
Venue
Istituto Italiano di Tecnologia
Via Morego, 30
16163 Genova
Course dates
5-6 December 2016
Remarks
Organized in collaboration with Prof. Giulio Sandini and Dr. Alessandra Sciutti.