Important factors in machine learning (IMAGE) Science China Press Caption The four important factors (feature, label, distribution, objective) of the machine learning process are shown in the figure. In conventional machine learning, all those factors are assumed to hold invariant. Credit ©Science China Press Usage Restrictions Use with credit. License Original content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.