 Google Machine Learning Interview Questions And Answers. Here Coding compiler sharing a list of 25 interview questions on Google machine learning. These Google ML interview questions were asked in various interviews by top MNC companies and prepared by expert Machine learning professionals. We hope that these Machine learning interview questions will help you to crack your next Google Machine Learning job interview. All the best for your future and happy machine learning.

## Google Machine Learning Interview Questions

1. What is A/B testing in Machine Learning?
2. What is activation function in Machine Learning?
3. What is Rectified Linear Unit (ReLU) in Machine learning?
4. What is sigmoid function in Machine learning?
6. What is AUC (Area under the ROC Curve) in machine learning?
7. What is backpropagation in machine learning?
8. What is baseline in machine learning?
9. What is batch in machine learning?
10. What is model training in machine learning?

1) What is A/B testing in Machine Learning?

A) A statistical way of comparing two (or more) techniques, typically an incumbent against a new rival. A/B testing aims to determine not only which technique performs better but also to understand whether the difference is statistically significant. A/B testing usually considers only two techniques using one measurement, but it can be applied to any finite number of techniques and measures.

2) What is activation function in Machine Learning?

A) A function (for example, ReLU or sigmoid) that takes in the weighted sum of all of the inputs from the previous layer and then generates and passes an output value (typically nonlinear) to the next layer.

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

A) An activation function with the following rules:

• If input is negative or zero, output is 0.
• If input is positive, output is equal to input.

4) What is sigmoid function in Machine learning?

A) A function that maps logistic or multinomial regression output (log odds) to probabilities, returning a value between 0 and 1.

A) A sophisticated gradient descent algorithm that rescales the gradients of each parameter, effectively giving each parameter an independent learning rate.

6) What is AUC (Area under the ROC Curve) in machine learning?

A) An evaluation metric that considers all possible classification thresholds.

7) What is backpropagation in machine learning?

A) The primary algorithm for performing gradient descent on neural networks. First, the output values of each node are calculated (and cached) in a forward pass. Then, the partial derivative of the error with respect to each parameter is calculated in a backward pass through the graph.
The Area Under the ROC curve is the probability that a classifier will be more confident that a randomly chosen positive example is actually positive than that a randomly chosen negative example is positive.

8) What is baseline in machine learning?

A) A simple model or heuristic used as reference point for comparing how well a model is performing. A baseline helps model developers quantify the minimal, expected performance on a particular problem.

9) What is batch in machine learning?

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

10) What is model training in machine learning?

A) Model training is the process of determining the best model.

11) What is batch size machine learning?

A) 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.

12) What is bias in machine learning?

A) An intercept or offset from an origin. Bias (also known as the bias term) is referred to as b or w0 in machine learning models.

13) What is a binary classification in machine learning?

A) A type of classification task that outputs one of two mutually exclusive classes. For example, a machine learning model that evaluates email messages and outputs either “spam” or “not spam” is a binary classifier.

14) What is bucketing in machine learning?

A) Converting a (usually continuous) feature into multiple binary features called buckets or bins, typically based on value range. For example, instead of representing temperature as a single continuous floating-point feature, you could chop ranges of temperatures into discrete bins. Given temperature data sensitive to a tenth of a degree, all temperatures between 0.0 and 15.0 degrees could be put into one bin, 15.1 to 30.0 degrees could be a second bin, and 30.1 to 50.0 degrees could be a third bin.

Google Machine Learning Interview Questions # 15) What is calibration layer in machine learning?

A) A post-prediction adjustment, typically to account for prediction bias. The adjusted predictions and probabilities should match the distribution of an observed set of labels.

Google Machine Learning Interview Questions # 16) What is candidate sampling in machine learning?

A) A training-time optimization in which a probability is calculated for all the positive labels, using, for example, softmax, but only for a random sample of negative labels. For example, if we have an example labeled beagle and dog candidate sampling computes the predicted probabilities and corresponding loss terms for the beagle and dog class outputs in addition to a random subset of the remaining classes (cat, lollipop, fence).

Google Machine Learning Interview Questions # 17) What is checkpoint in machine learning?

A) Data that captures the state of the variables of a model at a particular time. Checkpoints enable exporting model weights, as well as performing training across multiple sessions. Checkpoints also enable training to continue past errors (for example, job preemption). Note that the graph itself is not included in a checkpoint.

Google Machine Learning Interview Questions # 18) What is class in machine learning?

A) One of a set of enumerated target values for a label. For example, in a binary classification model that detects spam, the two classes are spam and not spam. In a multi-class classification model that identifies dog breeds, the classes would be poodle, beagle, pug, and so on.

Google Machine Learning Interview Questions # 19) What is class-imbalanced data set in machine learning?

A) 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.

Google Machine Learning Interview Questions # 20) What is classification model in machine learning?

A) A type of machine learning model for distinguishing among 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 regression model.

### Interview Questions on Google Machine Learning

21) What is classification threshold in machine learning?

A) 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.

Google Machine Learning Interview Questions # 22) What is collaborative filtering in machine learning?

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

Google Machine Learning Interview Questions # 23) What is confusion matrix in machine learning?

A) 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.

Google Machine Learning Interview Questions # 24) What is convergence in machine learning?

A) Informally, often refers to a state reached during training in which training loss and validation loss change very little or not at all with each iteration after a certain number of iterations.

In other words, a model reaches convergence when additional training on the current data will not improve the model. In deep learning, loss values sometimes stay constant or nearly so for many iterations before finally descending, temporarily producing a false sense of convergence.

Google Machine Learning Interview Questions # 25) What is convex function in machine learning?

A) 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. Source: Google Machine Learning