Scribd
Upload
11 views1 page

AIML Question Bank - Module 5

The document outlines the course details for 'Artificial Intelligence and Machine Learning' offered by the Electronics and Computer Science department, including the course code, semester, faculty name, and academic year. It lists 15 questions related to various topics in artificial neural networks, covering architecture, learning rules, types of networks, and performance evaluations. Each question is associated with a specific course outcome (CO) and Bloom's level (BL).

Uploaded by

yojanayadav
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
11 views1 page

AIML Question Bank - Module 5

The document outlines the course details for 'Artificial Intelligence and Machine Learning' offered by the Electronics and Computer Science department, including the course code, semester, faculty name, and academic year. It lists 15 questions related to various topics in artificial neural networks, covering architecture, learning rules, types of networks, and performance evaluations. Each question is associated with a specific course outcome (CO) and Bloom's level (BL).

Uploaded by

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

Department Name: Electronics and Computer Science

Course Name : Artificial Intelligence and Machine Learning Course Code : PCC-BES304
Semester : III
Faculty Name : Mrs. Sumitha V Academic Year : 2025-26
Module Coverage: 5
CO Coverage : CO5

[Link] Question COs BL


1 Explain the basic architecture of an Artificial Neural Network and compare it with the 5 2
structure of a biological neuron.

2 Describe the different components of an artificial neuron and explain the role of activation 5 2
functions with examples.
3 Explain the perceptron learning rule with a suitable diagram. How does the perceptron 5 2
classify linearly separable patterns?
4 Discuss different types of Artificial Neural Networks based on architecture and learning 5 2
style.
5 Differentiate between single-layer and multi-layer perceptrons in terms of structure and 5 2
learning capability.
6 Summarize the working principles of Multi-Layer Perceptron (MLP). Highlight how 5 2
hidden layers contribute to learning.
7 Describe Radial Basis Function (RBF) neural networks. How do RBF units differ from 5 2
sigmoid units?
8. Explain the architecture and working of a Self-Organizing Feature Map (SOFM). 5 2

9. Analyze the limitations of single-layer perceptrons and justify the need for multi-layer 5 3
perceptrons with an example problem.
10. Apply the backpropagation algorithm to compute one iteration of weight updates for a 5 3
given MLP with sample input, target, and initial weights.
11 Apply the delta rule to compute weight corrections for a given training sample in a 5 3
perceptron.
12 Evaluate the performance differences between RBF and MLP neural networks for 5 3
function approximation tasks.
13 compare competitive learning (SOFM) and supervised learning (MLP) with respect to 5 2
applications and learning dynamics.
14 Explain Kohonen’s learning rule used in Self-Organizing Maps. 5 2

15 Explain how weights and biases influence the output of a neural network. 5 2

You might also like