Scribd
Upload
280 views3 pages

Fundamentals of AI Answers

The document provides a question bank on the fundamentals of AI, covering topics such as intelligent agents, knowledge representation, expert systems, statistical pattern recognition, and various learning types. It discusses key concepts like Naïve Bayes model, discriminant functions, and the differences between generative and discriminative models. Additionally, it highlights specific AI technologies like ChatGPT and Gemini, along with their functionalities.

Uploaded by

Devansh Panchal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
280 views3 pages

Fundamentals of AI Answers

The document provides a question bank on the fundamentals of AI, covering topics such as intelligent agents, knowledge representation, expert systems, statistical pattern recognition, and various learning types. It discusses key concepts like Naïve Bayes model, discriminant functions, and the differences between generative and discriminative models. Additionally, it highlights specific AI technologies like ChatGPT and Gemini, along with their functionalities.

Uploaded by

Devansh Panchal
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Fundamentals of AI - Question Bank Answers

1. Write a Short Note on Intelligent Agent?


An Intelligent Agent is an entity that perceives its environment through sensors and acts upon it
using actuators. It can be simple, like a thermostat, or complex, like an AI chatbot. Types include
reactive agents, model-based agents, goal-based agents, and utility-based agents.

2. Explain Knowledge levels in NLP?


Knowledge levels in NLP include lexical (words and morphology), syntactic (grammar and sentence
structure), semantic (meaning of words and phrases), discourse (context and coherence), and
pragmatic (real-world application and user intent).

3. Write a note on Intelligent Agent.


An intelligent agent is a system that can make decisions autonomously based on data it receives
from its environment. It may use AI techniques like machine learning and reasoning to optimize its
actions.

4. What are the various approaches towards knowledge representation?


Approaches include:
1. Logical Representation - Uses formal logic.
2. Semantic Networks - Graph-based knowledge representation.
3. Frames - Data structures representing stereotypical situations.
4. Production Rules - IF-THEN rules.
5. Ontologies - Defines relationships between concepts.

5. List advantages and disadvantages of expert system.


Advantages:
- Provides expert-level decision-making.
- Reduces errors and increases efficiency.
- Can work 24/7 without fatigue.

Disadvantages:
- Limited to predefined knowledge.
- Cannot learn or adapt like humans.
- Requires expert knowledge to build.

6. Discuss Statistical Pattern recognition approach?


Statistical pattern recognition uses mathematical models to identify patterns in data. It relies on
probability theory, machine learning algorithms, and statistical techniques like Bayesian classifiers
and decision trees.

7. Difference between language understanding and language generation


Language understanding focuses on interpreting and extracting meaning from text or speech, while
language generation involves producing human-like text based on input data.

8. Explain about the techniques of representation and mappings


Techniques include:
- Symbolic Representation: Uses logic and symbols.
- Sub-symbolic Representation: Uses neural networks.
- Hybrid Representation: Combines multiple approaches for better accuracy.

9. Explain Naïve Bayes Model.


Naïve Bayes is a probabilistic classifier based on Bayes' theorem. It assumes independence
between features and is widely used for spam filtering and text classification.

10. What is Discriminant function?


A discriminant function is used in classification tasks to separate different classes. It assigns a class
to an input based on decision boundaries computed from training data.

11. Write Short note on Learning Types


1. Supervised Learning: Uses labeled data to train models.
2. Unsupervised Learning: Finds patterns in unlabeled data.
3. Reinforcement Learning: Uses rewards and penalties to train agents.

12. Explain Inductive learning method and process.


Inductive learning involves generalizing from specific training examples to form rules or models that
can be applied to unseen data.

13. Differentiate Generative and Discriminative models.


Generative models (e.g., Naïve Bayes) model the joint probability distribution of input and output.
Discriminative models (e.g., SVM, Logistic Regression) focus on decision boundaries between
classes.

14. Compare Biological neuron and Artificial neuron.


Biological neurons process information in the brain through electrical signals, while artificial neurons
are mathematical models used in neural networks to mimic brain functions.

15. Explain Artificial neural network along with computational unit.


Artificial Neural Networks (ANNs) consist of layers of artificial neurons (nodes) that process input
data. Each neuron applies a weighted sum followed by an activation function to determine output.

16. Explain the following:


1. ChatGPT: A generative AI chatbot developed by OpenAI using deep learning models.
2. Bashini: AI assistant developed for specific applications.
3. Krutrim: An AI model developed in India for regional applications.

17. Explain how Gemini works?


Gemini is an advanced AI model developed by Google DeepMind, integrating multimodal
capabilities to process and generate text, images, and other media efficiently.

You might also like