Could anyone help me on what basis the number of hidden layers are chosen for deep neural network.

2 ビュー (過去 30 日間)
jaah navi
jaah navi 2021 年 7 月 3 日
編集済み: Matt J 2021 年 7 月 5 日
Let me explain in brief.
I have generated the code for deep neural network for regression purpose using numerical data to predict the formation of clusters.
when I run the code, for four hidden layers i can get the lowest value of mean square error as compared to 2 hidden layers,3 hidden layers,5 hidden layers, and 6 hidden layers.
So,I can say four hidden layers are optimal in my case.
But I would like to know is there any other reason other the mean square error to justify why four hidden layers are optimal.
Also let me know, for an image based on pixel, I can find low level features, high level features and so on.
But for numerical data what represent low level and high level features.
Could anyone please clarify me.

回答 (1 件)

Matt J
Matt J 2021 年 7 月 3 日
編集済み: Matt J 2021 年 7 月 3 日
But I would like to know is there any other reason other the mean square error to justify why four hidden layers are optimal.
No, if you change the loss function or any other thing about your network architecture (e.g., number of neurons per layer), you could very well find you get a different optimal number of layers.
But for numerical data what represent low level and high level features.
In general, you won't know that in advance. The main purpose of a neural network is for the network to learn the relevant features on its own are during training.
  15 件のコメント
Matt J
Matt J 2021 年 7 月 5 日
Reason for what? If the results don't represent converged networks, there is no basis on which to compare them.

サインインしてコメントする。

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by