Hobson decomposes consciousness into 10 functional components which he briefly defines:
( in Scientific Approaches to Consciousness, Cohen and Schooler, Psychology Press, 1996, page 383 )
Attention: Selection of input data
Perception: Representation of input data
Memory: Retrieval of stored representations
Orientation: Representation of time, place, and person
Thought: Reflection upon representation
Narrative: Linguistic symbolization of representations
Emotion: Feelings about representations
Instinct: Innate propensities to act
Intention: Representations of goals
Volition: Decisions to act
My artificial intelligence Asa H performs all of these functions, some more completely than others.
Attention: See blogs of 1 June 2011, 21 June 2014, 15 October 2015 for
example.
Perception: This works well though we would like to have more input sensors.
Memory: Our case vector memory works well.
Orientation: Time is represented explicitly. Our self model can represent a person.
Asa can recognize where it is by its surroundings.
Thought: Extrapolation and other learning algorithms examine and operate on
the case memories.
Narrative: Asa has a simple natural language vocabulary but this is primitive
compared to that used by most humans.
Emotion: Asa has a pain circuit and an advanced value system. It does not
share all of our human emotions.
Instinct: Asa can have pain and reflexes, a drive to reproduce, etc.
Intention: Asa's value system defines its goals.
Volition: Asa acts so as to optimize its vector utility.
I believe that Asa is more conscious than humans in some ways* and less conscious in others.
* in that it has access to and control over some of its internal processes which humans don't.
Asa also has a much larger STM (short term memory) capacity.
No comments:
Post a Comment