Hidden layer and hidden neuron
显示 更早的评论
I have 106587 data (11843rows *9 columns). I need to predict one parameter (output) using 8 other parameters (inputs).
1) How many hidden layers should I use (2 or 3) ?
2) How many hidden neurons should I assign for each hidden layer?
I tried 2 hidden layers with random (1-20) hidden neurons each layer but huge amount of MSE obtained for training, validation and testing. Please explain why this happens?
回答（1 个）
Burhan Burak AKMAN
2021-12-27
0 个投票
Increase amount of hidden neurons to 100-200 and re-train. May be it will help.
类别
在 帮助中心 和 File Exchange 中查找有关 Electrophysiology 的更多信息
2021-12-27
2021-12-30
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
