Machine Learning Interview Questions and Answers Set 5

41. What is Rectified Linear Unit (ReLU) in Machine learning?

An activation function with the following rules:

(a). If the input is negative or zero, the output is 0.

(b). If the input is positive, the output is equal to input.

42. What is batch in machine learning?

The set of examples used in one iteration (that is, one gradient update) of model training.

43. What is batch size machine learning?

The number of examples in a batch. For example, the batch size of SGD is 1, while the batch size of a mini-batch is usually between 10 and 1000. Batch size is usually fixed during training and inference.

44. What is class-imbalanced dataset in machine learning?

A binary classification problem in which the labels for the two classes have significantly different frequencies. For example, a disease data set in which 0.0001 of examples have positive labels and  0.9999 have negative labels is a class-imbalanced problem, but a football game predictor in which  0.51 of examples label one team winning and 0.49 label the other team winning is not a class-  imbalanced problem.

45. What is the classification model in machine learning?

A type of machine learning model for distinguishing between two or more discrete classes. For example, a natural language processing classification model could determine whether an input sentence was in French, Spanish, or Italian. Compare with the regression model.

46. What is the classification threshold in machine learning?

A scalar-value criterion that is applied to a model’s predicted score in order to separate the positive class from the negative class. Used when mapping logistic regression results to binary classification.

47. What is collaborative filtering in machine learning?

Making predictions about the interests of one user based on the interests of many other users. Collaborative filtering is often used in recommendation systems.

48. What is the confusion matrix in machine learning?

An NxN table that summarizes how successful a classification model’s predictions were; that is, the correlation between the label and the model’s classification. One axis of a confusion matrix is the label that the model predicted, and the other axis is the actual label. N represents the number of classes.

49. What is the convex function in machine learning?

A function in which the region above the graph of the function is a convex set. The prototypical convex function is shaped something like the letter U.

A strictly convex function has exactly one local minimum point, which is also the global minimum point. The classic U-shaped functions are strictly convex functions. However, some convex functions (for example, straight lines) are not.

50. Which is better for image classification? Supervised or unsupervised classification. Justify.1

In a supervised classification, the images are interpreted manually by the ML expert to create feature classes whereas this is not the case in unsupervised classification wherein the ML software creates feature classes based on image pixel values. Therefore, it is better to opt for supervised classification for image classification in terms of accuracy.