How is a deep neural network different from other neural networks?

28

10

How is a neural network having the "deep" adjective actually distinguished from other similar networks?

kenorb

Posted 2016-08-02T16:59:30.683

Reputation: 9 163

Answers

30

The difference is mostly in the number of layers.

For a long time, it was believed that "1-2 hidden layers are enough for most tasks" and it was impractical to use more than that, because training neural networks can be very computationally demanding.

Nowadays, computers are capable of much more, so people have started to use networks with more layers and found that they work very well for some tasks.

The word "deep" is there simply to distinguish these networks from the traditional, "more shallow" ones.

Disenchanted Lurker

Posted 2016-08-02T16:59:30.683

Reputation: 785

I would like to point out that this "belief" that a neural network with just 1 hidden layer can compute any function is actually been proven (see e.g. http://neuralnetworksanddeeplearning.com/chap4.html). I think you should have explained a little bit more why more than 1 hidden layer is then "convenient".

– nbro – 2019-02-23T22:14:25.543

9

A deep neural network is just a (feed-forward) neural network with many layers.

However, deep belief networks, Deep Boltzmann networks, etc., are not considered (debatable) deep neural networks, as their topology is different (i.e. they have undirected networks in their topology).

See also this: https://stats.stackexchange.com/a/59854/84191.

Dawny33

Posted 2016-08-02T16:59:30.683

Reputation: 1 297