Artificial Intelligence and Machine Learning Quiz - CBSE Class 12 ICT

Free practice quiz: Artificial Intelligence and Machine Learning (CBSE Class 12 ICT). 12 multiple-choice questions with answers and explanations. Play online, no sign-up needed.

This CBSE Class 12 ICT practice quiz has 12 multiple-choice questions on Artificial Intelligence and Machine Learning, and 12 of them come with an explanation. Try the 5 sample questions below (tap an option to check yourself), then play the full quiz online. No sign-up needed.

Sample questions

1. What is the primary difference between Artificial Intelligence (AI) and Machine Learning (ML)?

   1. AI is a subset of ML
   2. ML is a subset of AI
   3. AI and ML are completely unrelated fields
   4. AI focuses on hardware, while ML focuses on software
   Show answer

   Answer: B. ML is a subset of AI

   Machine Learning is a specific approach to achieving Artificial Intelligence. AI is a broader concept encompassing various techniques, with ML being one of them.

2. Explain the concept of supervised learning in machine learning.

   1. The algorithm learns from unlabeled data.
   2. The algorithm learns from labeled data and feedback.
   3. The algorithm learns by interacting with an environment.
   4. The algorithm learns by trial and error without any data.
   Show answer

   Answer: B. The algorithm learns from labeled data and feedback.

   Supervised learning involves training an algorithm on a dataset where each data point is labeled with the correct output. The algorithm learns to map inputs to outputs based on these labeled examples.

3. Describe the difference between a shallow and a deep neural network.

   1. A shallow network has more layers than a deep network.
   2. A deep network has more layers than a shallow network.
   3. There is no difference; both terms refer to the same thing.
   4. The difference is in the type of data they process.
   Show answer

   Answer: B. A deep network has more layers than a shallow network.

   Deep neural networks have multiple hidden layers between the input and output layers, allowing them to learn more complex patterns and representations of data compared to shallow networks with fewer layers.

4. Discuss the ethical considerations surrounding the use of AI and ML, particularly concerning bias in algorithms.

   1. Ethical considerations are irrelevant to AI development.
   2. Bias is not a significant problem in AI algorithms.
   3. AI algorithms can reflect and amplify existing biases in data, leading to unfair or discriminatory outcomes.
   4. Bias in algorithms is easily detected and corrected.
   Show answer

   Answer: C. AI algorithms can reflect and amplify existing biases in data, leading to unfair or discriminatory outcomes.

   AI systems are trained on data, and if that data contains biases (e.g., racial, gender), the resulting algorithms will likely perpetuate and even exacerbate those biases. Addressing bias requires careful data curation, algorithm design, and ongoing monitoring.

5. Discuss the challenges in implementing explainable AI (XAI) and its importance in building trustworthy AI systems.

   1. XAI is simple to implement and readily available.
   2. XAI is not necessary for effective AI systems.
   3. Explaining complex AI models can be difficult, requiring new techniques and approaches.
   4. The importance of XAI is mainly theoretical, with no practical implications.
   Show answer

   Answer: C. Explaining complex AI models can be difficult, requiring new techniques and approaches.

   Many AI models, especially deep neural networks, are "black boxes", making it hard to understand how they arrive at their decisions. XAI aims to make these decisions transparent and understandable, crucial for building trust and accountability in AI systems.

More questions in this quiz

Answers and explanations are in the full quiz.

1. Which of the following is NOT a common application of machine learning?
2. What is a neural network in the context of AI?
3. Explain the concept of reinforcement learning.
4. What is 'overfitting' in machine learning, and how can it be mitigated?
5. Explain the concept of transfer learning in deep learning and its advantages.
6. Compare and contrast different AI model evaluation metrics, such as precision, recall, F1-score, and AUC-ROC, considering their suitability for different applications.
7. Analyze the impact of advancements in quantum computing on the future of artificial intelligence and machine learning, considering both potential benefits and challenges.

Browse all Emerging Technologies quizzes

More to play