Re^2: X-prize Suggestions here please!

Goal
Create a program that can learn like a baby/child with only plain text in 1 natural language (like english) as input and as output. The program will also respond as a baby, making more sense as it matures.

Criteria
The program must store associative information based on the input given. If the program gets input like: "A tree is green.", it must (learn to) store a connection between some entity "tree" and some other entity "green". The program may not have any hard-coded knowledge of verbs, nouns, adjectives etc.

Comment on Re^2: X-prize Suggestions here please!

Replies are listed 'Best First'.
Re^3: X-prize Suggestions here please! by dragonchild (Archbishop) on Oct 17, 2004 at 00:30 UTC
This kind of rule-based learning is the basis for intermediate level programs in languages such as Prolog. Being right, does not endow the right to be rude; politeness costs nothing. Being unknowing, is not the same as being stupid. Expressing a contrary opinion, whether to the individual or the group, is more often a sign of deeper thought than of cantankerous belligerence. Do not mistake your goals as the only goals; your opinion as the only opinion; your confidence as correctness. Saying you know better is not the same as explaining you know better.	[reply]

Replies are listed 'Best First'.

Re^3: X-prize Suggestions here please!
by dragonchild (Archbishop) on Oct 17, 2004 at 00:30 UTC

Being right, does not endow the right to be rude; politeness costs nothing.
Being unknowing, is not the same as being stupid.
Expressing a contrary opinion, whether to the individual or the group, is more often a sign of deeper thought than of cantankerous belligerence.
Do not mistake your goals as the only goals; your opinion as the only opinion; your confidence as correctness. Saying you know better is not the same as explaining you know better.

[reply]