1. fixed database/rulebase
no learning
no value function
An example would be an expert system.
2. learning
no value function
An example would be a typical neural network.
3. learning between generations only
value function used
An example would be certain genetic algorithms.
4. learning during the lifetime
value function used
An example would be a human (but humans have limited rationality, see, for instance
Predictably Irrational, Dan Ariely, Harper Collins,
2008, and a flawed value system founded on a few
simple drives and aversions).
Asa H may be a better example (having a better value system and being more rational
www.robert-w-jones.com, inventor, A.s.a.).
5. collective intelligences
An example might be a society (it has been known for 100 years that groups can make
better decisions than an individual can).
Another example may be a collection of Asa H agents.
No comments:
Post a Comment