© Hisham El-Amir and Mahmoud Hamdy 2020
H. El-Amir, M. HamdyDeep Learning Pipelinehttps://doi.org/10.1007/978-1-4842-5349-6_7

7. Data Resampling

Hisham El-Amir1  and Mahmoud Hamdy1
(1)
Jizah, Egypt
 

In statistics, resampling is the method that consists of drawing repeated samples from the original data. So, we can say that resampling methods are a tool taken from modern statistics. These methods involve repeatedly taking a sample from the training set and training the model on each sample in order to get additional information about the model.

For example, we can estimate variability of the learning of the model of interest. We can draw different samples from the training data, then each time we train the model on a given sample, we examine the difference ...

Get Deep Learning Pipeline: Building a Deep Learning Model with TensorFlow now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.