Connectionist networks can think without following rules
Like humans, connectionist networks exhibit fluid, intelligent behaviour without following rigid, explicit rules. In general, they are trained to exhibit intelligent behaviour rather than being programmed with rules.
Notes: Also see the"Do humans use rules as physical symbol systems do?" arguments on Map 3.
Terence Horgan and John Tiensen (1991) provide a full characterisation of classical and connectionist notions of rule following.
Fred Adams, Kenneth Aizawa, & Gary Fuller (1992) provide a detailed treatment of the relation between different kinds of rules, arguing that the differences between them should not be overstated.