One of the criticisms of neural networks (and of associative inference generally) is that it cannot generalize. See, for example, Fodor and Pylyshyn 1988. Of course in the 25 years since the criticism was leveled they have faced the sternest of all critics: empirical evidence to the contrary. This paper describes a neural net that can learn Newtonian physics. "Our results provide surprisingly strong evidence of IN's ability to learn accurate physical simulations and generalize their training to novel systems with different numbers and configurations of objects and relations."
Today: 0 Total: 4 [Direct link] [Share]
View full size
