1

Say I have a training set with 50 vectors. I split this set into 5 sets each with 10 vectors and then I scale the vectors in each subset and normalise the subsets. Then I train my ANN with each vector from each subset. After training is complete, I group my test set into subsets of 10 vectors each, scale the features of the vectors in each subset and normalise each subset and then feed it to the neural network to attempt to classify it.

Is this the right approach? Is it right to scale and normalise each subset, each with its own minimum, maximum, mean and standard deviation?

Avinash Shenoy
  • 63
  • 6
  • Maybe [batch normalization](https://arxiv.org/pdf/1502.03167.pdf) is interesting? – Thomas Wagenaar Jul 01 '17 at 12:20
  • But the classification isn't for the subset or batch, we're still trying to classify each vector. That paper seems to talk about classifying batches instead of individual vectors. – Avinash Shenoy Jul 01 '17 at 13:01

0 Answers0