ML-70 Quiz

Which is not a type of machine learning?

• Supervised Learning

• Self Learning

• Unsupervised Learning

• Reinforcement Learning

Answer explanation

Self Learning is not a type of machine learning. The correct answer is Self Learning.

What is an example of an application of unsupervised learning?

• 1. Predicting future stock prices based on historical data.

• 1. Document clustering to group similar documents together.

• Translating text from one language to another

• 1. Image recognition and classification using a trained model.

Answer explanation

Document Clustering is an example of an application of unsupervised learning where documents are grouped based on similarities without predefined labels.

Which statement best describes the concept of overfitting in machine learning?

• When the model performs well on training data but poorly on unseen data

• When the model performs consistently on all types of data

• When the model has too few parameters to learn from the data

Choose the wrong answer for the type of unsupervised learning

• Clustering

• Classification

• Association

Answer explanation

Classification is the wrong answer as it is a type of supervised learning, unlike clustering and association which are unsupervised learning techniques.

Which of the following is not true about K-Means Algorithm?

• It is used for unsupervised

• It is used for supervised

• Is a clustering algorithm

Answer explanation

The correct choice is 'It is used for supervised' as K-Means Algorithm is used for unsupervised clustering. K-Means is specifically designed for clustering, which is the process of grouping data points into clusters based on their similarity

Choose the correct statement

• Unsupervised learning is used for data has labels

• Supervised learning is used for data that has no labels

• Unsupervised learning is used for data that doesn't have a label

Answer explanation

Unsupervised learning is used for data that doesn't have a label, making it the correct statement.

How many layers does an Artificial Neural Network have?

• 1 Layer

• 2 layers

• 3 layers or more

Answer explanation

An Artificial Neural Network typically consists of 3 or more layers, including an input layer, one or more hidden layers, and an output layer.

What is the purpose of clustering algorithms in unsupervised learning?

• To predict outcomes based on labeled data

• To group similar data points together based on certain criteria

• To classify data into predefined categories

Answer explanation

Clustering algorithms in unsupervised learning are used to group similar data points together based on certain criteria, not to predict outcomes based on labeled data or classify data into predefined categories.

What is the purpose of dimensionality reduction in machine learning?

• To increase the complexity of the model

• To reduce the number of features while retaining important information

• To introduce noise into the data

Answer explanation

It helps simplify the models, thus improve computational efficiency, reduce noise, and mitigate the curse of dimensionality.

Which of the following is a common evaluation metric for classification algorithms?

• Silhoutte Score

• Accuracy

• Adjusted Rand Index

• Mean Absolute Error