Free · no sign-up
PracticeArea Practice →
🎓 Free CBSE Class 10 practice, questions, mock tests & solutions. No sign-up.

CBSE Class 10 Artificial Intelligence: Machine Learning, practice questions & solutions

Free CBSE Class 10 Artificial Intelligence practice questions on Machine Learning, with step-by-step solutions. This set has 21 questions (1-mark, 2-mark, 4-mark) modelled on the board blueprint, MCQs, assertion-reason and subjective. Practise them untimed or add them to a full mock test.

Practise this topic free Add to a mock test

What you'll practise

This set has 21 Machine Learning questions for CBSE Class 10 Artificial Intelligence, appearing as 1-mark, 2-mark, 4-mark questions across Section A, Section B, Section E. Examples include:

Machine Learning practice questions

Section A (1 mark) · Machine Learning
Which scenario best represents a regression problem?
  1. APredicting tomorrow's temperature
  2. BIdentifying whether an email is spam
  3. CGrouping customers by behaviour
  4. DRecognising faces in photos
Show answer & solution
Answer: Predicting tomorrow's temperature. (A) Regression predicts a continuous numeric value, such as temperature.
Section A (1 mark) · Machine Learning
Classifying an email as 'spam' or 'not spam' is an example of:
  1. AClassification
  2. BRegression
  3. CClustering
  4. DDimensionality reduction
Show answer & solution
Answer: Classification. (A) Predicting a category/label (spam vs not spam) is a classification task.
Section A (1 mark) · Machine Learning
Learning from data that has NO labels, by finding groups or patterns, is called:
  1. AUnsupervised learning
  2. BSupervised learning
  3. CReinforcement learning
  4. DRule-based learning
Show answer & solution
Answer: Unsupervised learning. (A) Unsupervised learning finds structure (e.g. clusters) in unlabelled data.
Section A (1 mark) · Machine Learning
Grouping customers into segments without pre-defined labels is an example of:
  1. AClustering (unsupervised learning)
  2. BClassification
  3. CRegression
  4. DReinforcement learning
Show answer & solution
Answer: Clustering (unsupervised learning). (A) Clustering groups similar items together and is a form of unsupervised learning.
Section A (1 mark) · Machine Learning
Which learning approach is most suitable for training an AI model to park a car correctly through trial and error?
  1. AReinforcement learning
  2. BSupervised learning
  3. CUnsupervised learning
  4. DTransfer learning
Show answer & solution
Answer: Reinforcement learning. (A) Learning by trial and error with rewards/penalties is reinforcement learning.
Section A (1 mark) · Machine Learning
Overfitting happens when a model:
  1. AMemorises the training data instead of learning general patterns
  2. BPerforms equally well on all data
  3. CIs too simple to learn anything
  4. DHas too little training data only
Show answer & solution
Answer: Memorises the training data instead of learning general patterns. (A) An overfitted model memorises the training data and fails to generalise to new data.
Section A (1 mark) · Machine Learning
Why do we split a dataset into a training set and a test set?
  1. ATo train on one part and fairly check performance on unseen data
  2. BTo make the dataset smaller
  3. CTo delete half the data
  4. DTo avoid using any data
Show answer & solution
Answer: To train on one part and fairly check performance on unseen data. (A) The train-test split lets the model learn on one portion and be evaluated fairly on data it has not seen.
Section A (1 mark) · Machine Learning
In machine learning, 'error' is used to measure:
  1. AHow accurately the model predicts the data
  2. BThe speed of the computer
  3. CThe size of the dataset
  4. DThe number of columns
Show answer & solution
Answer: How accurately the model predicts the data. (A) Error measures how far the model's predictions are from the true values, its accuracy.
Section A (1 mark) · Machine Learning
Assertion (A): Using the same data for both training and testing gives a misleading idea of a model's performance.
Reason (R): A model may simply memorise data it has already seen, so testing on it hides overfitting.
Show answer & solution
Correct option: (Both A and R are true and R is the correct explanation of A). Both true and R explains A, reusing training data for testing hides overfitting, so the score is misleading.
Section B (2 marks) · Machine Learning
Give two differences between supervised and unsupervised learning.
Show answer & solution
(1) Supervised learning uses labelled data (inputs with known outputs); unsupervised learning uses unlabelled data. (2) Supervised learning predicts a label/value (classification or regression); unsupervised learning finds hidden structure such as clusters. Example: spam detection is supervised; customer segmentation is unsupervised.
Section B (2 marks) · Machine Learning
Explain the train-test split technique with respect to a machine-learning algorithm.
Show answer & solution
The train-test split divides the dataset into two parts: a training set (usually the larger part, e.g. 70 to 80%) used to teach the model, and a test set (the remaining 20 to 30%) kept aside. The model learns only from the training set, then its performance is measured on the unseen test set. This gives a fair estimate of how well the model will work on new data and helps detect overfitting.
Section A (1 mark) · Machine Learning
Learning from data that already has labelled answers is called:
  1. ASupervised learning
  2. BUnsupervised learning
  3. CReinforcement learning
  4. DManual learning
Show answer & solution
Answer: Supervised learning. (A) Supervised learning trains on labelled examples with known outputs.

Get more Machine Learning questions in the app →

How to revise Machine Learning

Attempt each question before opening the solution, note the marking-scheme keywords for written answers, and re-attempt anything you got wrong a day later. Then add Machine Learning to a full timed mock to practise it under exam conditions.

More CBSE Class 10 Artificial Intelligence

Keep going: sit the Artificial Intelligence mock test, skim the Artificial Intelligence revision sheet, or browse all Artificial Intelligence topics.

Model EvaluationIntroduction to AIAI Project CycleNatural Language ProcessingEmployability SkillsAI EthicsNeural NetworksComputer Vision

Related CBSE Class 10 subjects

CBSE Class 10 Data ScienceCBSE Class 10 Computer Applications
Original questions written for this site, modelled on the CBSE blueprint.

Frequently asked questions

How many marks is Machine Learning in CBSE Class 10 Artificial Intelligence?

In the practice set, Machine Learning appears as 1-mark, 2-mark, 4-mark questions across Sections Section A, Section B, Section E.

Where can I get free Machine Learning questions with answers?

PracticeArea offers 21 free Machine Learning questions for CBSE Class 10 Artificial Intelligence, each with the answer and a worked solution, on this page and in the practice app.

Are these Machine Learning questions the real board questions?

No, they are original questions modelled on the CBSE blueprint and marking scheme, so you can practise the format repeatedly.