The Cybenko theorem for neural networks
This theorem is a very important one in the neural nets theory.
Indeed, in 1989, George Cybenko proved that a single hidden layer feed forward neural network can approximate any continuous and multivariate function.
Moreover, he also proved that a failure with such neural nets would be caused by bad weights or learning rate, etc.
This theorem helps as it tells us that various functions can be approximated with neural networks.
Nice blog, i have added it to my favourites, greetings
I found your site on technorati and read a few of your other posts. Keep up the good work. I just added your RSS feed to my Google News Reader. Looking forward to reading more from you down the road!
Your blog is interesting!
Keep up the good work!