When does Matlab consider a Neural Network deep?

Question

Annette Mai 2021-1-26

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/727238-when-does-matlab-consider-a-neural-network-deep

评论： Walter Roberson 2021-1-30

I want to use a feedforward NN (FFNN) with at least two hidden layers. This is no problem with the feedforwardnet function. I also can train the net with the train function, where it says "Train shallow neural network". In most literature I read, a shallow NN is defiend as a NN with only one hidden layer and a deep NN is one with more than one hidden layer. For deep NNs Mathworks recomends trainNetwork as a train function. But I was not able to train my FFNN with this function.

So where does Mathworks draw the line between shallow and deep NNs? Or is there a way to train my FFNN with trainNetwork?

2 个评论
显示无隐藏无

Annette Mai 2021-1-26

在 MATLAB Online 中打开

I can delcare a FFNN with two hidden layers like this:

a = [1 2 3 4 5 6 7 8 9 10 7 8 9 10 11 12 13 14 15 16];
b = [7 8 9 10 11 12 13 14 15 16 1 2 3 4 5 6 7 8 9 10];
c = a.*b;
FFnet = feedforwardnet([3,4]);
FFnet = train(FFnet, [a;b], c)

Walter Roberson 2021-1-30

"Deep" for Neural Network seems to be much the same as "deep" for philosophy:

It claims to encompass pretty much everything
Hardly anybody really understands the logic behind it

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Rohit Pappu 2021-1-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/727238-when-does-matlab-consider-a-neural-network-deep#answer_609313

trainNetwork works with Deep Learning Layers. Additional Information can be found here

2 个评论
显示无隐藏无

Annette Mai 2021-1-29

So for Mathworks a feedfoward net with two hidden layers is not a deep neural net?!

Annette Mai 2021-1-29

I want to map a nonlinear equation with a NN. I´ve got data like in my other exampel a and b as Inputs and c as the resulting output. How could I load this data into the Deep Network Designer? All the examples seem to be about image processing.

请先登录，再进行评论。