How do you choose a neural network model for a particular purpose?

Question

I am a beginner with very less knowledge about CNN & RNN. For Eg: RNN works better for time series and CNN for spacial features, knowing this it might make easy for me to select between RNN and CNN. Though, if I am made to make a choice between ResNet, InceptionNet, etc for particular application, How do I get an intution of which would work better?

I wish there was a softdrink - instant knowledge... But its study - exercises, papers and tears/ sweat — Estradiaz, Oct 12 '19 at 10:26

score 0 · Answer 1 · answered Oct 13 '19 at 11:22

Please state your particular application if you want your answer in detail. But I if I want to answer you by considering your general question, I must state that: - It depends on your dataset (number of items and size of data), feature engineering and type of your features. - The evaluation measure of your particular application: like as accuracy, precision, recall, RMSE, F-measure and etc.

So, If you want to get intution about your network, it is better to run it on your data, if not, read the paper which has the same dataset as your own, and read the analyze part of paper.

But every neural network acts better in some kind of data. For example it is typical to use LSTM for sequential data.

score 0 · Answer 2 · answered Oct 13 '19 at 14:10

0

Experimentation Experimentation Experimentation

Get your hands dirty, you'll automatically get an intuition of which would work better.

answered Oct 13 '19 at 14:10

Ghost

450
3
14

How do you choose a neural network model for a particular purpose?

2 Answers2