The following definitions were contributed by members of euCognition in response to a questionnaire. If you haven't completed the questionnaire, please consider doing so.
The definitions are listed in the order in which they were submitted.
Cognition is the ability to relate perception and action in a meaningful way determined by experience,learning and memory.
A cognitive system possesses the ability of self-reflection (or at least self-awareness).
Cognition is gaining knowledge through the senses.
Cognition is the ability to ground perceptions in concepts together with the ability to manipulate concepts in order to proceed toward goals.
An artificial cognitive system is a system that is able to perceive its surrounding environment
with multiple sensors, merge this information, reason about it, learn from it and interact with the outside world.
A machine is said to be a cognitive system if a human observer cannot detect a difference between
the behavior of this machine and the behavior of an evolved animal (either human or animal relative).
Cognition is self-aware processing of information.
Cognitive systems are systems with knowledge-based behavior.
Cognitive Systems are ones that are able to extract and (most importantly)
represent useful aspects of largely redundant, possibly irrelevant sensory information in
a form that is most conducive to achieving a particular high level goal.
A cognitive system should be defined by its capability of finding the relationship
of some or all the information coming from its inputs (sensors) in order to generate the best
(internal or external) outputs after comparing this information with previously "memorized" input-output patterns.
Cognition is the act of segmenting and recognizing a perceptual event and grounding (binding) it to a symbol (meaning).
Cognition is autonomous conjectural (fallible) symbol grounding. (Symbols may, of
course, take varied physical forms, including continuous and distributed...)
Cognitive systems are systems that control learned "automatic" mappings between sensory stimuli and motor behavior by integrating internal states and intentions.
Cognition is a process of search for an appropriate action by an intelligent agent.
An (artificial) cognitive system is one that uses intelligent control, generally modelled on high-level biological intelligent systems;
common features are memory, learning, and a capacity for planning.
An artificial cognitive system is an embodied computer.
It is designed by people to realize a cognitive task.
The aim of the design is to construct a system producing a behavior that is qualified by system's
designers as a reasonable behavior performing the task at hand.
What is a cognitive task depends on the designers.
A cognitive system is a system that can change its behaviour based on reasoning, using observed evidence and domain knowledge.
Cognition is when I know what I am doing, when I can judge how good or bad it is, and explain why I am doing it.
Cognitive systems are systems with open niche spaces, capable of (some degree of)
decoupling from immediate stimuli, and of (flexibly) controlling the degree
to which internal representations and environmental input feed information processing,
so as to remain within the state space of survivability.
Cognition is the state of mind when we understand something without being able to define it.
(If cognition were definable, it would be implementable in a Turing machine).
A Cognitive System is an artificial system designed to carry out tasks in the real world
which are sufficiently complex to require (i) knowledge acquisition by real-world sensing,
(ii) learning, prediction and planning, and (iii) real-world interaction.
A cognitive system (is a system that) can modify its behaviour on the basis of experience so as to achieve specific anti-entropic ends.
A system is "cognitive" if it is able to act or reason adequately
(in terms of externally observable standards) in response to its perception of its environment,
using principles and concepts learned through its interaction with its environment.
Cognition is a mapping from sensation (present and past) to
current action which achieves a specific condition robustly across
significant perturbations of the external mapping from action
(present and past) to current sensation.
Cognition is the ability to plan, reason, adapt and act according to high level motivations or goals and
using a range of senses, typically including vision, and may be communicate
A cognitive system is one that is able to perceive, learn, reason, plan and
express itself through language and action and do so intentionally, i.e.
it must be able to understand the intentionality of others and demonstrate intentionality when engaged in communication.
Human capabilities activated due to perception, which are enhanced with learning and reasoning skills
and wich implies a physical reaction within the environment.
The cultural context, within which cognition is performed, plays an important role, too.
Cognition is a set of information-processing capacities that allow to flexibly act in a complex environment
A cognitive system is an autonomous anti-entropy engine.
A cognitive system is a system capable of abstracting significant environmental facts, in different time scales, from the here and now of embodied dynamic interaction.
Cognition does not describe any well-defined state, relation, thing, or event. Once we have a vocabulary to express the dynamic embedding of perceiving and acting agents in a rich environment, the term will be redundant.
Cognition is the process of achieving a goal by a process of perception, modelling, planning and acting which does not exclude the pursuit of sub-optimal paths and strategies
Any system able to interact with external cues (cognitive or not) and to learn from experience
A System that interacts with the real-world, develops some notion of "self" and acts in the world to preserve this Self.
Cognitive is any system that has the following characteristics:
A cognitive system is able to interpret sensations through abstraction, i.e. its responses may not be directly correlated with the sensations. Furthermore, a cognitive system is able to evolve by building new abstractions, depending on its goals. Finally, the construction and evolution of a cognitive system needs to be efficient, contrasting a system with pre-programmed responses to all the sensations it might encounter.
Cognitive systems are systems that are capable of acquiring, extending, and justifying knowlege.
Cognition falsifies the homunculus fallacy.
Cognition: the algorithms and representations that determine fitness.
Cognitive systems are machines capable of linking symbolic forms to the physical states of their material parts. They do so autonomously and inherently.
Cognition is the same as life. Life is not definable. As a living system operates it is making cognitive acts. Observer's eye sees all that stuff (including observer too).
Finally, here is a commentary by Aaron Sloman on the validity of this exercise.
In science, arguing about a definition and attempting to produce a single binary division (e.g. between cognitive and non-cognitive systems/processes/mechanisms) is often a waste of time.
What we need are surveys of the variety of possibilities, and comparative analysis of their implications, requirements, tradeoffs, etc. (The philosopher Gilbert Ryle referred to analysing the 'logical geography' of a system of concepts.)
Instead of futile and unending debates about which is the best or right definition to use we can do more fruitful research into similarities and differences between many different subcases, whether in natural or artificial systems. For example, many definitions of cognition consider only human capabilities and would exclude the ability of insects to use landmarks.
I am not saying there is a continuum of cases: on the contrary both in evolution and in the set of possible artificial systems there are many interesting discontinuities -- some big some small. We need to understand all of them. Focusing on one division that happens to interest particular researchers can divert research away from the more general kind research which in the long run will provide deeper insights into all the discontinuities.