Machine Learning Concepts

Question 1

What is machine learning?

Answer 1

A field of AI where systems learn from data to make predictions or decisions.

Question 2

What are the main types of machine learning?

Answer 2

Supervised, Unsupervised, and Reinforcement Learning.

Question 3

What is supervised learning?

Answer 3

Learning from labeled data to predict outcomes.

Question 4

What is unsupervised learning?

Answer 4

Learning patterns from unlabeled data.

Question 5

What is reinforcement learning?

Answer 5

Learning by interacting with an environment to maximize cumulative reward.

Question 6

What is a labeled dataset?

Answer 6

A dataset where each input is paired with the correct output.

Question 7

What is a feature?

Answer 7

An individual measurable property or characteristic of data.

Question 8

What is a label?

Answer 8

The output variable or the value to be predicted.

Question 9

What is a model?

Answer 9

A mathematical representation of a real-world process learned from data.

Question 10

What is training data?

Answer 10

Data used to train a machine learning model.

Question 11

What is test data?

Answer 11

Data used to evaluate the accuracy of a trained model.

Question 12

What is validation data?

Answer 12

Data used to fine-tune model parameters during training.

Question 13

What is overfitting?

Answer 13

When a model learns the training data too well and performs poorly on unseen data.

Question 14

What is underfitting?

Answer 14

When a model is too simple to capture the data’s structure.

Question 15

What is a decision tree?

Answer 15

A tree-like model used to make decisions based on input features.

Question 16

What is a random forest?

Answer 16

An ensemble of decision trees used to improve prediction accuracy.

Question 17

What is k-nearest neighbors (KNN)?

Answer 17

A method that classifies based on the majority class among k nearest data points.

Question 18

What is a support vector machine (SVM)?

Answer 18

A model that finds the optimal boundary that separates classes.

Question 19

What is a linear regression?

Answer 19

A model that fits a line to predict a continuous output.

Question 20

What is logistic regression?

Answer 20

A classification algorithm based on the logistic function.

Question 21

What is classification?

Answer 21

Predicting discrete labels.

Question 22

What is regression?

Answer 22

Predicting continuous values.

Question 23

What is clustering?

Answer 23

Grouping similar data points together.

Question 24

What is dimensionality reduction?

Answer 24

Reducing the number of features while preserving information.

Question 25

What is principal component analysis (PCA)?

Answer 25

A technique for dimensionality reduction by projecting data onto principal components.

Question 26

What is a confusion matrix?

Answer 26

A table showing true positives, false positives, true negatives, and false negatives.

Question 27

What is accuracy?

Answer 27

The ratio of correct predictions to total predictions.

Question 28

What is precision?

Answer 28

The ratio of true positives to predicted positives.

Question 29

What is recall?

Answer 29

The ratio of true positives to actual positives.

Question 30

What is F1 score?

Answer 30

The harmonic mean of precision and recall.

Question 31

What is cross-validation?

Answer 31

A method for assessing model performance by dividing data into training and validation sets multiple times.

Question 32

What is k-fold cross-validation?

Answer 32

Dividing the dataset into k parts and using each as a validation set once.

Question 33

What is hyperparameter tuning?

Answer 33

Optimizing the settings that control the learning process.

Question 34

What is grid search?

Answer 34

A method for tuning hyperparameters by exhaustively searching a predefined set of values.

Question 35

What is random search?

Answer 35

A method for tuning hyperparameters by sampling random combinations.

Question 36

What is model evaluation?

Answer 36

Measuring a model's performance using various metrics.

Question 37

What is data preprocessing?

Answer 37

Cleaning and transforming data before feeding it into a model.

Question 38

What is feature scaling?

Answer 38

Normalizing data so features contribute equally to model performance.

Question 39

What is normalization?

Answer 39

Rescaling features to a range of [0, 1].

Question 40

What is standardization?

Answer 40

Transforming features to have mean 0 and standard deviation 1.

Question 41

What is feature selection?

Answer 41

Choosing the most relevant features for modeling.

Question 42

What is the bias-variance tradeoff?

Answer 42

The balance between underfitting and overfitting.

Question 43

What is a learning curve?

Answer 43

A plot showing training and validation accuracy over time.

Question 44

What is a ROC curve?

Answer 44

A graph showing the trade-off between true positive rate and false positive rate.

Question 45

What is AUC?

Answer 45

Area Under the ROC Curve — a measure of model quality.

Question 46

What is a baseline model?

Answer 46

A simple model used for comparison.

Question 47

What is data leakage?

Answer 47

When information from outside the training dataset is used to create the model.

Question 48

What is a pipeline?

Answer 48

A sequence of data preprocessing and modeling steps applied consistently.

Question 49

What is ensemble learning?

Answer 49

Combining predictions from multiple models to improve performance.

Question 50

What is boosting?

Answer 50

An ensemble technique that combines weak learners sequentially to form a strong learner.

Question 51

What is bagging?

Answer 51

An ensemble method that trains multiple models independently and combines their results.