LINEAR ALGEBRA AND OPTIMIZATION
FOR MACHINE LEARNING CERTIFICATION
EVALUATION EXAMS SET FULL QUESTIONS
AND COMPLETE SOLUTION
●● Vector
Answer: Quantity with direction and magnitude, used in machine
learning.
●● Matrix
Answer: Two-dimensional array fundamental in linear algebra.
●● Gradient Descent
Answer: Iterative optimization algorithm to minimize function error.
●● Area Under the Receiver Operating Characteristic (ROC) curve
Answer: A graphical representation of the trade-off between true positive
rate and false positive rate for a binary classification model.
●● Singular Value Decomposition (SVD)
Answer: Factorization of a matrix into three other matrices.
, ●● Hyperparameter
Answer: Parameters of a ML model set before training.
●● Information Theory
Answer: In feature selection, mutual information measures the
dependency between a feature and the target variable; low mutual
information indicates that the feature provides useful information.
●● Convolution
Answer: Operation blending two functions, used in image processing.
●● Principal Component Analysis (PCA)
Answer: Dimensionality reduction technique for identifying important
features.
●● Probability Distribution
Answer: Mathematical function describing likelihood of obtaining
values in a random experiment.
●● Entropy
Answer: Measure of uncertainty or disorder in a system.
●● Regression
FOR MACHINE LEARNING CERTIFICATION
EVALUATION EXAMS SET FULL QUESTIONS
AND COMPLETE SOLUTION
●● Vector
Answer: Quantity with direction and magnitude, used in machine
learning.
●● Matrix
Answer: Two-dimensional array fundamental in linear algebra.
●● Gradient Descent
Answer: Iterative optimization algorithm to minimize function error.
●● Area Under the Receiver Operating Characteristic (ROC) curve
Answer: A graphical representation of the trade-off between true positive
rate and false positive rate for a binary classification model.
●● Singular Value Decomposition (SVD)
Answer: Factorization of a matrix into three other matrices.
, ●● Hyperparameter
Answer: Parameters of a ML model set before training.
●● Information Theory
Answer: In feature selection, mutual information measures the
dependency between a feature and the target variable; low mutual
information indicates that the feature provides useful information.
●● Convolution
Answer: Operation blending two functions, used in image processing.
●● Principal Component Analysis (PCA)
Answer: Dimensionality reduction technique for identifying important
features.
●● Probability Distribution
Answer: Mathematical function describing likelihood of obtaining
values in a random experiment.
●● Entropy
Answer: Measure of uncertainty or disorder in a system.
●● Regression
