CODEWITHSUNDEEP
machine-learningneural-networknormalization
Bastian
Bastian

Reputation: 1593

Data/Feature normalization

I've a set of features within the interval (-1,1). I'm looking for a bijective function or a procedure to normalize the data to a certain range with a mean close to 0 and a variance close to 1.

It's very import that the function is bijective since I need the features normalized as input for a neutral network with tanh activation function. My process would be to in-memory transform the data, feed them to the net and to transform the network result back to the initial scale.

Upvotes: 2

Views: 392

Answers (1)

Marcin Możejko
Marcin Możejko

Reputation: 40506

This normalization task is quite usual in neural network aplications. The most common approach is to simply compute the mean and the standard deviation of your data and store that values in your training program. So the pipeline for your data is then:

  1. Compute mean and sd of your input data and store it in memory.
  2. Apply normalizing transformation : normed_data = (data - mean) / sd.
  3. Train / evaluate / use the network.
  4. Denormalize data using : original_data = (normed_data * sd) + mean.

I wrote a longer post on data normalization. You may read it here.

Upvotes: 2

Related Questions