attention schema theory
In plain wordsA theory that the brain keeps a simplified sketch of its own attention, and that our feeling of having an inner awareness is simply how that sketch portrays attention.
A theory of consciousness proposed by the neuroscientist Michael Graziano, on which the brain constructs a simplified model of its own attention — an attention schema — in order to monitor and control attention, much as it builds a body schema to control the limbs. Because the model is a sketch, it depicts attention not as a mechanistic competition among signals but as an inner, nonphysical awareness that takes hold of things; our conviction that we have subjective experience, and our reports of it, reflect the content of this model. The same machinery, applied to other people, supports theory of mindtheory of mind, n.: Being able to work out what someone else believes, wants or knows — even when it is not what you believe — and to use that to guess what they will do next. Researchers test whether AI has it.. AST is often classed with illusionismillusionism, n.: The view that the inner glow of experience that seems so hard to explain is a kind of trick the brain plays on itself: we are conscious, but not in the mysterious way it seems., and because it is mechanistic, Graziano argues that an AI system with an attention schema would be conscious in the same sense people are, and that building one could also improve its control of attention.
Origin
Introduced by Michael Graziano with Sabine Kastner in 'Human Consciousness and Its Relationship to Social Neuroscience: A Novel Hypothesis' (Cognitive Neuroscience, 2011), and developed in Graziano's books Consciousness and the Social Brain (2013) and Rethinking Consciousness (2019).
Related
- illusionismillusionism, n.: The view that the inner glow of experience that seems so hard to explain is a kind of trick the brain plays on itself: we are conscious, but not in the mysterious way it seems.
- theory of mindtheory of mind, n.: Being able to work out what someone else believes, wants or knows — even when it is not what you believe — and to use that to guess what they will do next. Researchers test whether AI has it.
- higher-order theories of consciousnesshigher-order theories of consciousness, n.: Theories holding that a mental state is conscious when the mind, in effect, notices it — when some further thought or perception represents you as being in that state.
- indicator properties of consciousnessindicator properties of consciousness, n.: A checklist of design features that leading scientific theories link to consciousness, used to judge how likely it is that a particular AI system could be conscious.
- machine consciousnessmachine consciousness, n.: Whether a machine such as an AI system could have genuine experiences of its own — and the research field that tries to find out, or to build such a machine.
- attentionattention, n.: A way for an AI model to choose what to focus on. For each word it processes, the model scores how relevant every other word is and draws information mostly from the relevant ones.
Sources
- Graziano, M. S. A. & Kastner, S. (2011). Human Consciousness and Its Relationship to Social Neuroscience: A Novel Hypothesis. Cognitive Neuroscience 2(2), 98–113.
- Graziano, M. S. A. (2013). Consciousness and the Social Brain. Oxford University Press.
Mentioned in
attentionattention, n.: A way for an AI model to choose what to focus on. For each word it processes, the model scores how relevant every other word is and draws information mostly from the relevant ones., theory of mindtheory of mind, n.: Being able to work out what someone else believes, wants or knows — even when it is not what you believe — and to use that to guess what they will do next. Researchers test whether AI has it., illusionismillusionism, n.: The view that the inner glow of experience that seems so hard to explain is a kind of trick the brain plays on itself: we are conscious, but not in the mysterious way it seems., indicator properties of consciousnessindicator properties of consciousness, n.: A checklist of design features that leading scientific theories link to consciousness, used to judge how likely it is that a particular AI system could be conscious.