Connectionist computers lack commonsense

Connectionist networks are unable to make generalisations and classifications in the way human beings do, because they lack our commonsense understanding of the world.

For example, one of the army’s early connectionist networks was trained to distinguish photos of tanks from photos of empty landscapes.

The results were initially promising, but it was later discovered that the network made its generalisations inappropriately—by detecting whether or not their were clouds in the picture (the pictures with and without tanks had been taken on different days).

Note: For similar arguments applied to the symbol systems architecture, see the "Can a symbolic knowledge base represent human understanding?" arguments on Map 3.
 
Hubert Dreyfus, 1992.
RELATED ARTICLESExplain
Artificial Intelligence
Can computers think? [1]
Yes: connectionist networks can think [5a]
Connectionist computers lack commonsense
Hubert Dreyfus
Connectionist networks can think without following rules
The Connectionist Biological Assumption
The Connectionist Dilemma
The Subsymbolic Paradigm
Connectionist networks are formal systems
Connectionists fall into a computational mindset
One-layer perceptrons can’t compute certain functions
Graph of this discussion
Enter the title of your article


Enter a short (max 500 characters) summation of your article
Enter the main body of your article
Lock
+Comments (0)
+Citations (0)
+About
Enter comment

Select article text to quote
welcome text

First name   Last name 

Email

Skip