I am interested to see what advantages a Loop Network (Feed Forward Network that takes its output as input, I think it's called an RNN, not sure). The only result I found was that it was extremely sensitive to context, but only the context behind it. Other than that, I did not notice any changes.
I figured this would be better for a language processing unit, or one used to make inferences based upon it.
What are the shortcomings of each? Advantages?