ML-MSCCSA

List the three main types of machine learning

• Supervised learning

• Unsupervised learning

• Reinforcement learning

• Transfer K learning

1. In unsupervised learning, the model is trained with input-output pairs.

• False
• True

Which of the following is a supervised learning problem?

• 
  a) Customer segmentation
  

• b) Predicting house prices
  

• c) Market basket analysis
  

• d) Dimensionality reduction

What does VC dimension measure in a hypothesis class?

• The VC dimension measures the capacity of a hypothesis class to shatter sets of points.
• The VC dimension assesses the accuracy of shatters and predictions made by a hypothesis class.

• The VC dimension indicates the number of parameters in a model and shatter.

• The VC dimension measures the speed of learning in a hypothesis class.

If a classifier can shatter any set of 3 points in 2D, what is its VC dimension?

• 5
• 4
• 2
• 3

Regression algorithms are used to solve regression problems in which there is a l_____relationship between input and output variables.

Expand PAC in machine learning context.

• Potentially Accurate Classification
• Probably Approximately Correct
• Probably Approximate Correct

• Probable Algorithmic Complexity

What is noise in the dataset

• Noise in the dataset is random errors or irrelevant information that obscures the true signal.
• Noise is the error process of cleaning the dataset.

• Noise refers to the data points that are always accurate. and sometimes incorrect

• Noise is the main signal in the dataset.

Regression is used when the output variable is ______.

• ordinal
• binary
• continuous
• categorical

A model with low bias and high variance is likely to _______ the training data