mikael
Reputation: 2317
Neural network time series normalization
I am using LSTM as the hidden layer function in a time series prediction network. Is input normalization necessary? If it is, is data = data / sum(data) the correct normalization? Should the output also be normalized with the inputs?
Upvotes: 1
Views: 1449
Answers (1)
Lucas
Reputation: 2689
Is input normalization necessary?
No, but it might make your network converge faster. Use this calculation to scale your values to [0,1]:
.
Should the output also be normalized with the inputs?
No, I can't think of a reason why you would ever want to do that.
Upvotes: 2
Related Questions
- Finding patterns in time series with PyTorch
- Pattern recognition in time series using LSTM(python)
- Normalizing data in a time series classification problem - Recurrent Neural Networks
- Python - how to normalize time-series data
- Pybrain time series prediction using LSTM recurrent nets
- Normalizing time series measurements
- LSTM Timeseries Classification
- Forecasting time series data with PyBrain Neural Networks
- Normalize Time Series - Scikit
- Prediction using Recurrent Neural Network on Time series dataset