Scribd
Upload
24 views4 pages

Machine Learning One Mark Answers

The document provides concise answers to various machine learning concepts, including definitions of unsupervised learning, regression, confidence intervals, and types of learning. It also explains techniques like Naïve Bayes, Random Forest, and the EM algorithm, along with applications of machine learning and methods for model evaluation. Additionally, it covers advanced topics such as kernel machines, decision trees, and ensemble methods.

Uploaded by

2745manikanta
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
24 views4 pages

Machine Learning One Mark Answers

The document provides concise answers to various machine learning concepts, including definitions of unsupervised learning, regression, confidence intervals, and types of learning. It also explains techniques like Naïve Bayes, Random Forest, and the EM algorithm, along with applications of machine learning and methods for model evaluation. Additionally, it covers advanced topics such as kernel machines, decision trees, and ensemble methods.

Uploaded by

2745manikanta
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
You are on page 1/ 4

Machine Learning One-Mark Answers

Image 1 – Descriptive Questions


 Q: What is Unsupervised Learning?

A: Unsupervised learning is a type of machine learning where the model is trained on data
without labeled responses. The algorithm tries to identify hidden patterns or intrinsic
structures in the input data, commonly using techniques like clustering (e.g., K-Means,
DBSCAN) and dimensionality reduction (e.g., PCA).
 Q: What is Regression?

A: Regression is a statistical method used in supervised learning that estimates the


relationship between a dependent (target) variable and one or more independent (input)
variables. It is used to predict continuous outcomes, such as prices, temperatures, or
probabilities.
 Q: Define Confidence Interval.

A: A confidence interval is a range of values, derived from a dataset, that is likely to contain
the value of an unknown population parameter. It is associated with a confidence level (e.g.,
95%), indicating the probability that the interval includes the true parameter.
 Q: How to Estimate Binomial Proportions?

A: Binomial proportions can be estimated by dividing the number of successes (x) by the
total number of trials (n), i.e., p̂ = x/n. To estimate with a confidence interval, one can use
methods like the Wald interval or Wilson score interval.
 Q: When to Use Naïve Bayes Classifier?

A: Naïve Bayes is most effective when the input features are conditionally independent
given the class label. It is widely used in text classification, spam filtering, sentiment
analysis, and recommendation systems due to its simplicity and efficiency.
 Q: What is Maximum Likelihood Estimation (MLE)?

A: MLE is a statistical technique used to estimate the parameters of a probabilistic model. It


identifies the parameter values that maximize the likelihood function, which measures how
likely the observed data is given a set of parameters.
 Q: What is Random Forest?

A: Random Forest is an ensemble learning method that constructs a multitude of decision


trees during training and outputs the class (classification) or mean prediction (regression)
of the individual trees. It reduces overfitting and improves generalization by using random
feature selection and bagging.
 Q: What is EM Algorithm?

A: The Expectation-Maximization (EM) algorithm is an iterative optimization technique


used for parameter estimation in probabilistic models, particularly where data is
incomplete or has missing values. It consists of two steps: the Expectation (E) step and the
Maximization (M) step.
 Q: List out Various Types of Learnings.

A: 1. Supervised Learning
2. Unsupervised Learning
3. Semi-Supervised Learning
4. Reinforcement Learning
5. Self-Supervised Learning
 Q: In What Way Boosting is Different from Bagging?

A: Bagging trains multiple models in parallel using random subsets and aggregates their
results (e.g., Random Forest), while Boosting trains models sequentially, where each new
model focuses on correcting the previous model’s errors (e.g., AdaBoost). Boosting reduces
bias, while bagging reduces variance.

Image 2 – Concept-Based Questions


 Q: List out Various Machine Learning Applications.

A: Spam detection, fraud detection, disease diagnosis, recommendation systems,


autonomous driving, speech and facial recognition, customer segmentation, and predictive
maintenance.
 Q: What is Supervised Learning?

A: Supervised learning involves training a model on a labeled dataset, where the input data
is paired with the correct output. It is used for tasks like classification and regression.
 Q: Define Variance.

A: Variance in machine learning refers to the amount by which the model’s predictions
would change if it were trained on a different dataset. High variance often indicates
overfitting.
 Q: What is Confidence Interval?

A: A confidence interval gives a range of values within which a population parameter is


expected to fall, with a certain probability (e.g., 95%). It reflects the uncertainty of an
estimate.
 Q: What are Kernel Machines?
A: Kernel machines, such as Support Vector Machines (SVMs), use kernel functions to
implicitly map input features into higher-dimensional spaces to capture non-linear patterns.
 Q: What is Bayesian Belief Network?

A: A Bayesian Belief Network is a probabilistic graphical model that represents variables


and their conditional dependencies via a directed acyclic graph. It is used in reasoning
under uncertainty.
 Q: Define Vector Quantization.

A: Vector Quantization is a clustering-based technique that partitions input data into


clusters and represents each point by the centroid of its cluster. It is used in compression
and classification.
 Q: Expand DBSCAN.

A: DBSCAN stands for Density-Based Spatial Clustering of Applications with Noise.


 Q: What is Feature Extraction?

A: Feature extraction transforms raw data into meaningful features to improve learning
accuracy and efficiency. Examples include PCA and LDA.
 Q: What is Decision Tree Learning?

A: Decision Tree Learning uses a tree structure where nodes represent tests on attributes
and leaves represent decisions or outputs. It’s used for classification and regression.

Image 3 – Explanatory Questions


 Q: Mention Three Types of Machine Learning.

A: 1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning
 Q: Explain About Confidence Interval.

A: A confidence interval is a statistical range, with a specified probability, that a parameter


lies within the range. For example, a 95% confidence interval suggests a 95% chance the
true parameter lies within it.
 Q: Explain Decision Tree Representation.

A: A decision tree consists of internal nodes representing tests on features, branches


representing outcomes of the test, and leaves representing predicted outcomes. It is built
top-down using metrics like Gini Index or Information Gain.
 Q: Explain About Multi Linear Regression.
A: Multiple Linear Regression models the linear relationship between one dependent
variable and multiple independent variables. It’s used to predict a variable based on
multiple features.
 Q: What is Meant by Kernel?

A: A kernel is a function that maps data to a higher-dimensional space to make it linearly


separable. It is used in algorithms like SVM to handle non-linear relationships.
 Q: What is Dimensionality Reduction and Its Importance?

A: Dimensionality reduction is the process of reducing the number of features in a dataset


while preserving essential information. It improves model performance and reduces
overfitting and computation time.
 Q: How to Choose the Value of k in KNN?

A: Choose k using cross-validation to balance bias and variance. Small k may lead to
overfitting; large k may oversimplify. Odd values are often preferred for classification.
 Q: Explain the Use of SVM.

A: Support Vector Machines (SVMs) are supervised models used for classification and
regression. They work by finding the optimal hyperplane that separates data classes with
maximum margin.
 Q: Explain the Need for Ensemble Methods.

A: Ensemble methods improve model performance by combining predictions from multiple


models. They reduce bias, variance, or both, and increase robustness. Examples include
Bagging and Boosting.
 Q: Why DBSCAN?

A: DBSCAN is used because it can detect clusters of arbitrary shapes, does not require the
number of clusters in advance, and identifies noise points (outliers).

You might also like