ABSTRACT
Understanding machine-learning algorithms requires knowledge of basic concepts related to probability, statistics, and linear algebra. Machine learning is used to solve difficult mathematical problems which cannot easily be solved using simple algorithms. Most engineering analyses aim to infer the effects (output) from the cause (input). Many machine-learning algorithms have strong foundations in probability and statistics. Common statistical parameters that are used in the analysis of data include mean, variance, and standard deviation, whose definitions can be found in elementary textbooks on statistics. Essential mathematics required for understanding machine learning techniques is introduced in the chapter. The significance of covariance, correlation, and other statistical parameters in solving engineering problems is illustrated with examples. The application of Bayes’ theorem is also explained using examples from engineering.
