If you increase the number of hidden layers in a multi-layer Perceptron, the classification error of test data always decreases.

In a neural network, which of the following techniques is used to deal with overfitting?

For an image recognition problem (recognizing a cat in a photo), which architecture of neural network would be better suited to solve the problem?

Select non-linear activation functions from below

Which of the below are optimization functions

Recommender system which relies on past user-item interactions to make new predictions is

Recommender system approach which learns from existing features to explain user-item is

Which of the following is not a part of text normalization process

TF-IDF penalizes heavily words that occur very frequently in a document

TF-IDF penalizes heavily words that occur very frequently across multiple documents – true or false

Anomaly detection can be achieved using which approaches

Which field emerged to address the problem of learning functions from data without explicit programming?

Which of the following is true about Deep Learning?

Markov decision process is a type of

Regression is a form of feature learning

Image recognition is one of the typical application of anomaly detection

Which of the following cannot be used for time-series forecasting?

Similarity Learning is

Clustering is not a form of feature learning