Data preparation
Before data can be used to design a neural network, four steps in data preparation might be applied.

1. Raw data is first collected.
2. In the data processing step, the dataset can be cleaned by removing corrupted and incorrect records. Transformation techniques may be used to achieve useful features or to reduce data dimensions. Categorical variables in the dataset are also converted to numerical values that can be used.
3. Data labelling might be applied to label targets.
4. Dataset is then divided into three sets: Training set is used to train a neural network, a validation set is used to prevent the over-fitting issue, and the test set is used to evaluate how well the trained neural network could cope with completely new data-set
ANNHUB data format

The collected data must be presented in comma-separated values (CSV) format.
The first row is the header that includes inputs and targets' names.
Note: Target's header name must include keyword "output", "target" or "class"
Each following row represents a data sample or an observation.
Note: You can have as many inputs and outputs as you want.