Hi Wisam Mohammed Abed Alqaraghuli ,
The scaling method you should choose depends on your type of data, the kind of ANN your will implement (classifier or regressor), and the activation function that the AAN will use in the input-output layer.
Thus, if you are using Sklearn in Python check the [StandardScaler function](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html)
Best regards
Dear Wisam Mohammed Abed Alqaraghuli ,
Deep learning neural networks learn how to map inputs to outputs from examples in a training dataset.
The weights of the model are initialized to small random values and updated via an optimization algorithm in response to estimates of error on the training dataset.
Given the use of small weights in the model and the use of error between predictions and expected values, the scale of inputs and outputs used to train the model are an important factor. Unscaled input variables can result in a slow or unstable learning process, whereas unscaled target variables on regression problems can result in exploding gradients causing the learning process to fail.
https://machinelearningmastery.com/how-to-improve-neural-network-stability-and-modeling-performance-with-data-scaling/
Regards,
Shafagat
- Badges
- Science topic
- Similar topics
- Chemistry
- Nanotechnology
- Nanostructures
- Thin Films