I have many samples of a arrays representing signals in the time domain that I want to classify using artificial neural networks. Do I need to use feature extraction methods (such as the FFT or WT) before applying them to the ANN ? or do I apply the signal directly as it is (600 dim array) to the NN.
Thanks in advance.
Its depends the kind of data that you are analyzing, if it is noisy for sure you need to use feature extraction. Also feature extraction reduce the size of the input data reducing your models computational load and complexity , but add some extra work. In the end it is a commitment decision because you must take into consideration a number of aspects such as those that I comment you before and others regarding to the application.
Please look at the class
Artificial intelligence
from
MIT
on
YouTube
by
Winston
- Badges
- Science topic
- Similar topics
- Statistics
- Time Series