We conclude Part IV and advanced symbol-based problem solving with the presentation of several techniques for reasoning in uncertain situations. Drawing useful conclusions from incomplete and imprecise data using unsound reasoning methods is an important human skill; we do it very successfully in almost every aspect of life. We deliver correct medical diagnoses and recommend treatment from ambiguous symptoms; we analyze problems with our cars and stereos; we comprehend language statements that are often ambiguous or incomplete; we recognize friends from their voices and their gestures; and so on. For computers to be intelligent, they must have some of these same skills.