Scribd
Upload
9 views2 pages

Key Concepts in Machine Learning

The document provides definitions and explanations of key concepts in machine learning, including machine learning itself, least squares methods, Bayesian regression, overfitting, random forests, K-Nearest Neighbors, unsupervised learning, Gaussian mixture models, ensemble learning, and bootstrapping. It outlines the advantages and limitations of various methods and algorithms. Overall, it serves as a concise overview of important machine learning techniques and their applications.

Uploaded by

Kotti Karthikeyan
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
9 views2 pages

Key Concepts in Machine Learning

The document provides definitions and explanations of key concepts in machine learning, including machine learning itself, least squares methods, Bayesian regression, overfitting, random forests, K-Nearest Neighbors, unsupervised learning, Gaussian mixture models, ensemble learning, and bootstrapping. It outlines the advantages and limitations of various methods and algorithms. Overall, it serves as a concise overview of important machine learning techniques and their applications.

Uploaded by

Kotti Karthikeyan
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Q. No.

Define Machine Learning.

Machine learning is a branch of artificial intelligence that enables


1 algorithms to uncover hidden patterns within datasets. It allows
them to predict new, similar data without explicit programming for
each task
Interpret how different least squares methods can be applied to a
dataset to determine the best-fit line.

2 Least Squares method is a statistical technique used to find the


equation of best-fitting curve or line to a set of data points by
minimizing the sum of the squared differences between the
observed values and the values predicted by the model.
Interpret the advantages and disadvantages of Bayesian
Regression.
Advantages
Effective for small datasets
Handles uncertainty
Flexible modeling
3
Robust against outliers
Facilitates model selection
Limitations of Bayesian Regression
Computationally expensive.
Requires specifying priors

Recall ‘Over fitting’ in Machine learning.

Overfitting means creating a model that matches (memorizes) the


4
training set so closely that the model fails to make correct
predictions on new data.

Define random forest.

A Random Forest is a collection of decision trees that work together


5 to make predictionsRandom Forest algorithm is a powerful tree
learning technique in Machine Learning to make predictions and
then we do voting of all the tress to make prediction
6 Analyze the difference between the strengths and weaknesses of
the K-Nearest Neighbors (KNN) algorithm.
Advantages Limitations
Simple implementation High memory requirements
No training phase Computationally expensive for large
datasets
Adaptable to new data Sensitive to irrelevant features
Effective for small datasets. Struggles with imbalanced classes

What do you mean by Unsupervised learning?

Unsupervised learning is a branch of machine learning that deals


7 with unlabeled [Link] machine learning algorithms
find hidden patterns and data without any human intervention,
i.e., we don’t give output to our model

What are Gaussian mixture models. How is expectation


maximization used in it?

A Gaussian mixture model is a soft clustering technique used in


8 unsupervised learning to determine the probability that a given
data point belongs to a cluster. To fit a Gaussian Mixture Model to
the data, we use the Expectation-Maximization (EM) algorithm,
which is an iterative method that optimizes the parameters of the
Gaussian distributions
Define ensemble learning.

Ensemble learning combines the predictions of multiple models


9 (called "weak learners" or "base models") to make a stronger,
more reliable prediction. The goal is to reduce errors and improve
performance.
Define Bootstrapping.

10 Bootstrapping is a statistical procedure that resamples a single


data set to create many simulated samples.

You might also like