All terms Risks and failure modes
Bias
تعصب
Roman Urdu: ta'assub
Established A settled Urdu term already exists and is widely understood.
Definition
Systematic unfairness in a model's outputs, usually inherited from the data it was trained on.
تعریف
ماڈل کے نتائج میں مستقل ناانصافی، جو عام طور پر اس ڈیٹا سے آتی ہے جس پر اسے تربیت دی گئی ہو۔
Last reviewed: . Reviewer: Muhammad Asadullah.