Advertisement

Artificial Neural Networks

Started by September 09, 2009 12:01 PM
71 comments, last by Victor-Victor 15 years, 4 months ago
Quote:
Original post by Victor-Victor
I don't understand what do you mean by "toy example" and "not practical suggestion". Is it true or not? ANN research was stuck frozen for 30 years just because everyone assumed ANN can't do XOR. =


This is utter bs. ANN's can do XOR no problem. One layer networks can't because xor is not linearly separable. No one was stupid enough to think that an ANN cannot learn XOR, you just couldn't do it with one line in 2d space.
Quote:
Original post by ibebrett
Quote:
Original post by Victor-Victor
I don't understand what do you mean by "toy example" and "not practical suggestion". Is it true or not? ANN research was stuck frozen for 30 years just because everyone assumed ANN can't do XOR. =


This is utter bs. ANN's can do XOR no problem. One layer networks can't because xor is not linearly separable. No one was stupid enough to think that an ANN cannot learn XOR, you just couldn't do it with one line in 2d space.


Do not underestimate the power of human stupidity.


http://en.wikipedia.org/wiki/Perceptron
http://en.wikipedia.org/wiki/Perceptrons_(book)

In 1969 a famous book entitled Perceptrons by Marvin Minsky and Seymour Papert showed that it was impossible for these classes of network to learn an XOR function. They conjectured (incorrectly) that a similar result would hold for a perceptron with three or more layers.

Often-cited Minsky/Papert text caused a significant decline in interest and funding of neural network research. It took ten more years until neural network research experienced a resurgence in the 1980s.

The XOR affair - Critics of the book state that the authors imply that, since a single artificial neuron is incapable of implementing some functions such as the XOR logical function, larger networks also have similar limitations, and therefore should be dropped. Later research on three-layered perceptrons showed how to implement such functions, therefore saving the technique from obliteration.


Yes, people are stupid. They can blindly believe even the most ridiculous of books, if you only convince them it was written by some authority, Minsky in this particular case. Yes, people do not think, they will believe Sun revolves around the Earth, and they will put you in jail if you think otherwise. Now, look back at the history of science and you will realize nothing has changed since then. "All truth goes through three stages. First it is ridiculed, then it is violently opposed, finally it is accepted as self-evident."(Schopenhauer)

This topic is closed to new replies.

Advertisement