Scroll down to the bottom of the page to download the PDF
Chapter 1:
1. Define Artificial Intelligence, Neural Networks, Expert Systems, and Fuzzy Systems.
2. Explain types of Artificial Intelligence (Based on Capabilities and Functionalities).
3. List down artificial intelligence areas.
4. Briefly explain expert systems and neural networks.
5. Write down various applications of AI in different domains
6. Explain AI ethics and its limitations.
7. What is NLP? List out its Applications.
8. What is the Fuzzy Logic system? List out its key components.
9. Difference between Narrow AI and Weak AI
Chapter 2:
1. Define Machine Learning and explain its types.
2. Define the following terms:
a. Well-posed Learning Problem
b. Machine Learning
c. Classification
d. Regression
e. Clustering
f. Association Analysis
3. What are the questions involved in solving problems with well-posed methods? Explain each step in brief.
4. Write the difference between supervised, unsupervised, and reinforcement learning
5. Explain types of reinforcement learning. (Difference also.)
6. Explain approaches to implement Reinforcement Learning.
7. Explain value-based, policy-based, and model-based approaches to reinforcement learning.
8. List out all elements of reinforcement learning and explain each component.
9. Write Key Features of Reinforcement Learning.
10. Explain Supervised learning with their types.
11. Explain UnSupervised learning with their types.
12. Explain formalism with suitable examples
Chapter 3:
1. Explain/Difference between biological Neurons and Artificial Neurons
2. What is activation function and why use them in neural networks?
3. Explain ReLU, Sigmoid, and Hyperbolic tangent functions in neural networks.
4. Explain a single-layer feed-forward network and its application, advantages, and disadvantages
5. Explain the Multi-layer feed-forward network with its application, advantages, and disadvantages.
6. Explain recurrent networks with their application, advantages, and disadvantages.
7. Explain the learning process in ANN with all four factors.
8. Write a short note on Backpropagation.
9. Draw and explain the architecture of the Recurrent neural network.
10. Comparison between ANN and BNN.
11. Explain how data and information move through the network’s layer.
12. Explain the components of neurons.
Chapter 4:
1. What is NLP? Write the advantages and disadvantages of NLP.
2. Write the difference between Natural Language Understanding (NLU) and Natural Language Generation (NLG).
3. Write down applications of NLP.
4. Explain all the phases of NLP in detail.
5. Explain Lexical Ambiguity, Syntactic Ambiguity, and Referential Ambiguity. (Read remaining also at once)
6. Explain stemming words and parts of speech(POS) tagging with suitable example
7. Difference between stemming and Lemmatization.
8. Explain the Filtering of Stop Words in detail.
9. Discuss data processing using the NLTK library.
10. What do you mean by Crorpus in NLP?
11. Discuss what is the NER and WORDNET.
12. Explain the Frequency distribution of words in detail.
Chapter 5:
1. What is the word embedding technique?
2. Define the term word embedding and list various word embedding techniques.
3. Explain Term Frequency– Inverse Document Frequency (TFIDF), Bag Of Words (BoW), Word2Vec.
4. Calculate the TF and IDF for the below example. [He is Walter], [He is William], [He isn’t Peter or Walter]
5. Write Short Notes on GloVe.
6. List out all applications of NLP and explain any three.
7. Explain the calculation of TF(Term Frequency) for a document with a suitable example.
8. Explain the Inverse Document Frequency (IDF).
9. List out and explain each challenge of TF-IDF and BOW
Post a Comment