higher-order theories of consciousness
In plain wordsTheories 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.
A family of theories on which a mental state is conscious when it is suitably represented by another mental state, so that the subject is in some way aware of being in it; states not so represented, such as subliminal perceptions, remain unconscious. Higher-order thought theories, notably David Rosenthal's, require a thought to the effect that one is in the state; higher-order perception or 'inner sense' theories (David Armstrong, William Lycan) posit a quasi-perceptual monitoring faculty; and computational variants such as Hakwan Lau's perceptual reality monitoring identify consciousness with a metacognitive mechanism that tells reliable perceptual signals from noise or imagination. These theories tie consciousness to metacognitionmetacognition, n.: Thinking about one's own thinking: knowing what you know and don't know, judging how confident to be, and noticing when you have made a mistake. and to the prefrontal cortex, and they supply several 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. used to assess AI systems.
Origin
Rooted in John Locke's 'internal sense'; given modern form by David Armstrong (1968) and by David Rosenthal, whose 'Two Concepts of Consciousness' (Philosophical Studies, 1986) set out the higher-order thought theory. Hakwan Lau, Richard Brown and Joseph LeDoux developed empirical and computational versions in the 2010s.
Usage note
Common objections are that higher-order theories make consciousness too sophisticated for infants and many animals, and that a higher-order state might misrepresent a first-order state that does not exist.
Related
- metacognitionmetacognition, n.: Thinking about one's own thinking: knowing what you know and don't know, judging how confident to be, and noticing when you have made a mistake.
- introspectionintrospection, n.: Looking inward to observe your own thoughts and feelings. For AI, the question is whether a model can accurately report what is actually happening inside it, rather than guessing or making it up.
- global workspace theoryglobal workspace theory, n.: A leading scientific theory holding that we become conscious of something when the brain broadcasts it widely — as if putting it on a stage where every part of the mind can use it.
- consciousnessconsciousness, n.: Having experiences: there being something it feels like to be you, as when you see red or feel pain. Whether any AI is or could become conscious is an open and fiercely debated question.
- 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.
Sources
- Rosenthal, D. M. (1986). Two Concepts of Consciousness. Philosophical Studies 49(3), 329–359.
- Brown, R., Lau, H. & LeDoux, J. E. (2019). Understanding the Higher-Order Approach to Consciousness. Trends in Cognitive Sciences 23(9), 754–768.
Mentioned in
consciousnessconsciousness, n.: Having experiences: there being something it feels like to be you, as when you see red or feel pain. Whether any AI is or could become conscious is an open and fiercely debated question., introspectionintrospection, n.: Looking inward to observe your own thoughts and feelings. For AI, the question is whether a model can accurately report what is actually happening inside it, rather than guessing or making it up., attention schema theoryattention schema theory, n.: A 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., 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., metacognitionmetacognition, n.: Thinking about one's own thinking: knowing what you know and don't know, judging how confident to be, and noticing when you have made a mistake.