Cognitive Science 170
Natural and Artificial Symbol-Using Systems
Name: _________________________
SHORT PAPER #1:
Questions: (3-6 pages). Choose question 1 or 2! Indicate at beginning
of paper which question you have chosen! Hand in a printout on real
paper. Don't send an email attachment.
- 1. Fodor and Pylyshyn argue that current network models are
inadequate to explain certain aspects of human cognition. Summarize
and evaluate one or two of their main arguments.
- 2. Turing's original idea of computation was automated
conscious calculation by a human. As higher level computer
languages and compilers were developed, the connection between
the underlying machine language and the constructs of higher
level languages grew more distant. Many people (e.g., Allen
Newell) have argued that this separation between lower level
hardware and upper level cognitive architecture is crucial
to understanding human cognition (e.g., you can run the same
program on different kinds of hardware). Evaluate this idea.
In both cases, you can argue either side of the issue. I won't penalize
you for taking either side (or for arguing for something in between).
However, you must cite a few examples of both connectionist
and more traditional artificial intelligence models (like the ones
presented in class but not limited to them) to support your arguments.
A few good examples will make your task easier -- and it will make your
paper easier to read than the one by Fodor and Pylyshyn.
Finally, it is almost always a good idea to start each paragraph with
a topic sentence. A good test of the organization of your paper is to
read just the topic sentences one after the other.
due beginning of class Fri, 1/30/04