4 votes
Accepted

Are biases necessary to make neural networks universal approximators when using sigmoid activations?

No, you don't need a bias. You can have a "dummy" input (input(n+1) in your formualtion) which is always set to 1. Then the bias term is absorbed into the weights.
Aryeh's user avatar
  • 10.5k
3 votes

Can neural networks be used to devise algorithms?

According to this blog By Reza Zadeh, training a neural network to produce correct output even for just two-thirds of the training examples is computationally hard: Indeed, in 1988 J. Stephen Judd ...
Mohammad Al-Turkistany's user avatar
2 votes

Can neural networks be used to devise algorithms?

It seems the answer must be positive, because what might a reasonable negative answer to "Can neural networks be used to devise algorithms?" look like? If you accept the premise that human ...
Aryeh's user avatar
  • 10.5k
2 votes
Accepted

Are single hidden-layered neural networks at least as good as multi hidden-layered neural networks?

Short answer: Not necessarily. Likely nothing fishy is going on. Longer answer: The Universal Approximation Theorem (UAT) says nothing about an individual network's capacity to approximate a function....
Christian Bueno's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible