I am always studying.
I'm trying Deep Q learning with Chainerrl.
Tell me about data standardization.
If a continuous variable takes a value between -10 or less and 10 or more across 0 as shown in the following list:
How should we standardize it?
Since we are going to use it with nominal variables separated by (0, 1), we want to make the values of other continuous variables also in the range of 0 to 1. What should I do?
Although it seems that the values are almost in the range of -10 to 10, the exact value is the minimum and maximum values.
Should I normalize -10 or less as -10 and 10 or more as 10?
[-0.0023340981421771097, 10.10886891470353441, -0.8278840168666244, 0.0, -10.17769576921076302, 0.0, 0.0, 0.0, 0.0, -1.4023147212763036, 0.0, 0.0, 0.0]
Answer # 1
Mathematically, if you want to change from -10 to 10 from 0 to 1, you will have to translate by a factor of 20 times from -0.5 to 0.5 and then the whole translation by 0.5.
I just feel that it has a standardized function.
If you don't know the maximum and minimum values, you can find each data.
- python - (tensorflow) does the amount of learning change automatically depending on the difference between gpu and cpu or the am
- Tensorflow example of loading some variables
- Pre-defined variables for PHP learning (examples explained)
- Detailed tensorflow implementation of transfer learning examples
- Python tensorflow learning example of recognition of a single picture
- Convolutional neural network CNN for TensorFlow deep learning
- TensorFLow saves and restores variables with Saver
- tensorflow create variables and find variables by name
- Python uses tensorflow deep learning to identify verification codes
- Detailed TensorFlow methods to view variables in ckpt
- Go language learning packages and variables
- tensorflow print variables in memory method
- (beginner among machine learning beginners) please tell me how to actually test with tensorflow
- TensorFlow Session Session Control&Variable Variables
- Analysis of text classification in tensorflow learning tutorial
- Solve tensorflow error due to uninitialized variables
- Initializing some variables in the case of Tensorflow custom loss
- TensorFlow basic constants, variables and arithmetic operations in detail
- tensorflow - i want to see a graph of machine learning loss using tensorboardx
- Print tensorflow to restore all variables and operation nodes in the model
- machine learning - what is the "method" of deep learning? ?
- python - machine learning program slows down
- python 3x - how to create pre-processing data for deep learning
- python - creating a learning model using mnist (deep learning)
- python 3x - the error "input dimension is wrong" appears in keras cnn
- cuda - about the reason why loss does not decrease in u-net
- python - cifar-10 how to output correct rate for each class
- python 3x - the number of dimensions of input_data in nn using python-keras does not match
- tensorflow - consideration from loss function and accuracy rate