Data Preprocessing

• Dataset size limited only by available memory
• Input data types: numerical and categorical
• Automatic preprocessing before training
• Automatic numerical columns scaling
• Automatic categorical columns encoding

Training

• Automatic problem type determination (classification or regression)
• Automatic network training
• Full control of the training process, including pausing and stopping

Network Application

• The ability to save and load a network at any time you need
• Use a just created or loaded network to apply it to new data and get neural network reply

General

• Low resource requirements
• Example programs included in source form
• Support of load and save operations
• The Online Manual includes Chapter "Introduction in Neural Networks"