SRM University AP, Andhra Pradesh

Neerukonda, Mangalagiri Mandal,

Guntur District, Mangalagiri, Andhra Pradesh – 522240.

Artificial Intelligence
L T P C
Course Code CSE 455 Course Category Stream Electives (SE)
3 0 1 4
Pre-Requisite Progressive
CSE 201 Co-Requisite Course(s)
Course(s) Course(s)
Course Offering Professional / Licensing
CSE
Department Standards

Course Objectives / Course Learning Rationales (CLRs)

1. To enhance comprehension of both the theory that underpins and the accomplishments of artificial intelligence.
2. To introduce the concepts of a Rational Intelligent Agent and the different types of Agents that can be designed to solve
problems.
3. To review the different stages of development of the AI field from human like behaviour to Rational Agents.
4. To impart basic proficiency in representing difficult real-life problems in a state space representation so as to solve them
using AI techniques like searching and game playing.
5. to develop an awareness of the fundamental problems with knowledge representation, logic, blind and heuristic search,
and other subjects like minimum, resolution, etc. that are crucial to AI systems.
6. To introduce advanced topics of AI such as planning, Bayes networks, natural language processing and Cognitive
Computing.

Course Outcomes / Course Learning Outcomes (CLOs)

Expected Expected
Bloom’s
At the end of the course the learner will be able to Proficiency Attainment
Level
Percentage Percentage
Outcome 1 Identify the Intelligent systems and Approaches. 1 75% 65%
Discuss the building blocks of AI as presented in terms of intelligent
Outcome 2 2 75% 65%
agents.
Formalize the problem as a state space, graph, design heuristics and
Outcome 3 4 75% 65%
select amongst search or game-based techniques to solve them.
Develop intelligent algorithms for constraint satisfaction problems
Outcome 4 5 75% 65%
and intelligent systems for Game Playing.
Outcome 5 Implement application-specific intelligent systems 3 75% 65%
Represent logic-based techniques to perform inference and planning
Outcome 6 6 75% 65%
in given problems.

Course Articulation Matrix (CLO) to Program Learning Outcomes (PLO)

Program Learning Outcomes (PLO)

Project Management
Analysis, Design and

Multicultural Skills

Life Long Learning

Moral, and Ethical
Environment and

Self-Directed and
Modern Tool and

Teamwork Skills

Communication
Individual and
Sustainability
Development

and Finance
Engineering

Society and
Knowledge

Design and

Awareness
CT Usage
Research

CLOs
Problem
Analysis

PSO 1

PSO 2

PSO 3
Skills

Outcome 1 3 3 3 3 3 1 2 2 2 2 2 2
Outcome 2 3 2 3 2 2 1 2 2 3 2 2 2
Outcome 3 3 3 3 3 2 1 2 2 2 2 2 2
Outcome 4 3 3 3 2 3 1 2 3 3 3 2 3
Outcome 5 3 3 3 3 2 1 2 2 3 2 2 2
Outcome 6 3 3 3 3 2 1 2 2 2 3 3 2
Average 3 3 3 3 2 1 2 2 3 2 2 3
Course Unitization Plan Theory
Required
Unit CLOs References
Unit Name Contact
No. Addressed Used
Hours
Unit 1 Introduction 9
What is Intelligence. 1 1 1, 2
Foundations and History of Artificial Intelligence. 1 1 1, 2
Applications of Artificial Intelligence. 1 2 1, 2
Types of Different Intelligent system. 1 2 1, 2
Intelligent Agents, Structure of Intelligent Agents. 1 1, 2 1, 2
Introduction to Machine Learning and categorization. 1 1, 2 1, 2
Introduction to Reinforcement Learning. 1 1, 2 1, 2
Introduction to Deep Learning. 1 1, 2 1, 2
Introduction to Agents 1 1 1, 2
Unit 2 Search Mechanisms & Constraint Satisfaction problems. 9
Introduction to Search (Single Agent). 1 1 1, 2
Introduction to Search (Two Agents). 1 1 1, 2
Introduction to State space. 1 1 1, 2
Searching for solutions. 1 2, 3 1, 2
Uniformed search strategies. 1 3, 4 1, 2
Informed search strategies. 1 3, 4 1, 2
Local search algorithms and optimistic problems Adversarial
1 3, 4 1, 2
Search.
Least commitment search. 1 3 1, 2
Constraint satisfaction problems. 1 2 1, 2
Unit 3 Knowledge Representation and Reasoning 9
Propositional Logic and Inference rules. 1 2 1, 2, 3, 4
Predicate Logic (first order logic). 1 2, 3 1, 2, 3, 4
Inference in FOL. 1 2, 3 1, 2, 3, 4
Rule-based system, Logical Reasoning. 1 2, 3 1, 2, 3, 4
Forward &Backward Chaining. 1 2, 3 1, 2, 3, 4
Knowledge Resolution. 1 3, 4 1, 2, 3, 4
AI languages and tools – Lisp. 1 5 1, 2, 3, 4
AI languages and tools –Prolog. 1 5 1, 2, 3, 4
AI languages and tools –CLIPS. 1 5 1, 2, 3, 4
Unit 4 Problem Solving and planning 9
Formulating problems. 1 1, 2 1, 2, 3, 4
Problem types 1 2 1, 2, 3, 4
Solving Problems by Searching. 1 3, 4 1, 2, 3, 4
Heuristic search techniques. 2 2, 3 1, 2, 3, 4
Constraint satisfaction problems. 1 3, 4 1, 2, 3, 4
Plan space, partial order planning, planning algorithms 1 3, 4 1, 2, 3, 4
Stochastic search methods. 1 4 1, 2, 3, 4
Tabu search, best first search. 1 4 1, 2, 3, 4
Unit 5 Learning 9
Overview of different forms of learning, Inductive tree 1 1 1, 2
Decision trees, rule- Game playing 1 2, 3 1, 2
Perfect decision game-based learning. 1 2, 3 1, 2
Neural networks. 1 3, 4, 5 1, 2
Reinforcement learning. 1 2, 4, 5 1, 2
Game playing: Perfect decision game. 1 3, 4 1, 2
Imperfect decision game. 1 3, 4 1, 2
Evaluation function. 1 3, 4 1, 2
Minimax, Alpha-beta pruning. 1 4, 6 1, 2
Total Theory Contact Hours 45
Course Unitization Plan Lab
Required
CLOs References
No. Lab Experiment Contact
Addressed Used
Hours
Artificial Intelligence Problem identification, PEAS description,
1 2 1 1, 2, 3
and Introduction to PROLOG
Study of facts, objects, predicates, variables, arithmetic operators,
2 4 2 1, 2
simple input/output, and compound goals in PROLOG
Study of string operations in PROLOG. Implement string
3 operations like substring, string position, palindrome, and 4 1, 2 1, 2, 4
implement all set operations (Union, intersection, complement).
Write a program for Usage of rules in Prolog. Create a family tree
program to include following rules 1. M is the mother of P if she is
a parent of P and is female 2. F is the father of P if he is a parent of
4 4 2, 3 1, 2
P and is male 3. X is a sibling of Y if they both have the same
parent. 4. Then add rules for grand-parents, uncle-aunt, sister and
brother.
Write programs for studying Usage of arithmetic operators in
Prolog.
a) Accept name of the student, roll no, his/her subject name,
maximum marks and obtained marks in the subject. (Take marks of
atleast 6 subjects). Compute the percentage of a student. Display his
5 result with other information. 4 4 1, 2, 3
b) Accept department, designation, name, age, basic salary, house
rent allowance (HRA) of an employee. Compute dearness
allowance (DA) which is 15% of basic salary. Determine the gross
salary (basic salary + HRA + DA) of the employee. Display all
information of the employee (Generate Payslip).
6 Implement a program for recursion and list in PROLOG 4 4, 5 1, 2, 4, 5
Write a program for studying usage of compound object and list in
Prolog.
a) Write a program to maintain inventory items using a compound
7 object: 4 5 3, 4, 5
i. Accept from user the details of at least 10 objects.
ii. Display from user the details of objects entered by user
b) Find and display odd and even numbers from a given input list.
Write a program to solve the following problems.
1. Write a prolog program to solve “Water Jug Problem”.
2. Write a program to implement a monkey banana problem.
8 4 5, 6 4, 5
3. Write a program to implement 8 Queens Problem.
4. Write a program to solve traveling salesman problem.
5. Write a program to solve water jug problem using LISP.
Total Lab Contact Hours 30
Learning Assessment (Theory)
Continuous Learning Assessments (30%) End Semester Exam
Bloom’s Level of Cognitive Task CLA-1 Mid-1 CLA-2 CLA-3 (30%)
(10%) (10%) (5%) (5%)
Remember
Level 1 40% 50% 40% 50% 30%
Understand
Apply
Level 2 40% 40% 40% 30% 50%
Analyse
Evaluate
Level 3 20% 10% 20% 20% 20%
Create
Total 100% 100% 100% 100% 100%

Learning Assessment (Lab)

Continuous Learning Assessments (20%) End Semester Exam (20%)
Bloom’s Level of Cognitive Task Lab Performance (15%)
Lab Record (5%)

Remember
Level 1 10% 50% 30%
Understand
Apply
Level 2 50% 30% 50%
Analyse
Evaluate
Level 3 40% 20% 20%
Create
Total 100% 100% 100%

Recommended Resources
1. Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Prentice Hall.
2. Charniak, E., & McDermott, D. (2002). Introduction to Artificial Intelligence. Pearson Education.
3. Nilsson, N. J. (2002). Artificial Intelligence: A New Synthesis. Morgan Kaufmann.
4. Pearl, J. (2009). Causality: Models, Reasoning and Inference (2nd ed.). Cambridge University Press.
5. Rich, E., Knight, K., & Nair, S. B. (2017). Artificial Intelligence (3rd ed.). McGraw Hill Education.

Other Resources
1. No Data

Course Designers
1. No Data
 SRM University AP, Andhra Pradesh
Neerukonda, Mangalagiri Mandal,
Guntur District, Mangalagiri, Andhra Pradesh – 522240.

Digital Image Processing

L T P C
Course Code CSE 456 Course Category Stream Elective (SE)
3 0 1 4
Pre-Requisite Progressive
CSE 336 Co-Requisite Course(s)
Course(s) Course(s)
Course Offering Professional / Licensing MathWorks License
Department CSE Standards for MATLAB software

Course Objectives / Course Learning Rationales (CLRs)

1. Understand the overview of the field of image processing.
2. Gain knowledge of the fundamental algorithms and how to implement them.
3. Prepare to read the current image processing research literature.
4. Gain experience in applying image processing algorithms to real problems.

Course Outcomes / Course Learning Outcomes (CLOs)

Expected Expected
Bloom’s
At the end of the course the learner will be able to Proficiency Attainment
Level
Percentage Percentage
Describe the process of image processing and techniques
Outcome 1 2 75% 75%
involved in image processing pipeline.
Outcome 2 Identify image enhancement techniques. 2 75% 70%
Illustrate the causes for image degradation and overview of
Outcome 3 3 70% 65%
image restoration techniques.
Apply spatial and frequency domain techniques
Outcome 4 3 70% 65%
for image compression.
Demonstrate extraction techniques for image analysis and
Outcome 5 3 75% 70%
recognition.
Develop an image processing application using feature
Outcome 6 5 65% 60%
extraction and representation
Outcome 7 Recognize the rapid advances in Machine vision. 2 70% 65%

Course Articulation Matrix (CLO) to Program Learning Outcomes (PLO)

Program Learning Outcomes (PLO)

Project Management
Analysis, Design and

Multicultural Skills

Life Long Learning

Moral, and Ethical
Environment and

Self-Directed and
Modern Tool and

Teamwork Skills

Communication
Individual and
Sustainability
Development

and Finance
Engineering

Society and
Knowledge

Design and

Awareness
CT Usage
Research
Problem

CLOs
Analysis

PSO 1

PSO 2

PSO 3
Skills

Outcome 1 3 3 3 - - - - - - - - - 3 2
Outcome 2 3 3 3 2 - - - - - - - 3 3
Outcome 3 3 3 2 - - - - - - - - - 3 2
Outcome 4 3 3 2 - - - - - - - - - 3 3
Outcome 5 3 3 2 - 2 - - - - - - - 3 3
Outcome 6 2 2 3 3 3 - - - - - - - 2 3
Outcome 7 3 3 1 - - - - - - - - - 3 3
Average 3 3 2 3 2 3 3
Course Unitization Plan Theory
Required
Unit CLOs References
Unit Name Contact
No. Addressed Used
Hours
Unit
Introduction 9
1
Introduction: What is digital image and DIP? History,
1,7 1
Applications of DIP
Key stages of Digital Image processing, 1
1,7 1, 4
Advances in machine vision application domain
Image sampling and quantization, spatial resolution, intensity
1 1
resolution
Relationship between pixels: neighbourhood, adjacency and 1
1 1
connectivity, Path, region boundary
Connected component labelling, Distance measure: Euclidian,
1 1
chess board, city block.
Image acquisition and Pre-processing, Intensity transformations, 1
2 1
spatial filtering
Image enhancement: Introduction, Point Processing- image
1 2, 6 1
negative, log transform, dynamic range compression.
Power law or gamma Transformation, gamma correction 2, 6 1
Piecewise linear transformation: contrast stretching, threshold, bit-
1 2, 6 1
plane slicing
Histogram processing: image histogram, histogram equalization 2, 6 1
Numerical on histogram equalization, histogram specification,
1 2 1
numerical on histogram specification
Spatial filters for smoothing operations: linear filters (average and
weighted average), order statistics (nonlinear) filters: median, 1 2, 6, 7 1
min, max filters.
Spatial filters for sharpening operations: Convolution vs.
correlation, objective (integration, differentiation, application of 1 2, 6 1
sharpening),
First order and second order derivative operators and their
1 2 1
response, Laplacian operator, unsharp masking,
Unit Filtering in the Frequency Domain,
9
2 Image Restoration
Frequency domain approach: low pass filtering, high pass
1 2 1, 2, 3
filtering, Laplacian, high boost filtering.
Image transform and its importance, Fourier transform, 1D FT, 1D
1 2 1, 2, 3
Discrete Fourier Transform (DFT)
2D DFT and its property, Holomorphic filtering 1 2 1, 2, 3
Image restoration: Fundamentals, 1 3 1, 2, 3
Noise models, example images affected with noise 1 3 1, 2, 3
Estimation of noise parameters models 1 3 1, 2
Restoration in presence of noise (Spatial domain techniques):
1 3 1, 2
mean filters, order statistics filters
Adaptive local noise filter, adaptive median filter 1 3 1, 2
Estimation of degradation function: (i) by observation, (ii) by
1 3 1, 2
experimentation (iii) mathematical modelling
Unit
Image Segmentation 9
3
Image segmentation: Fundamentals, point, line detection, 1 5, 6 1
Basic edge detection techniques, Hough transform 1 5, 6 1
Thresholding: Bi-modal and Multi-model Histogram, 1 5 1
Noise effect on thresholding, Illumination effect on image
1 5 1
thresholding
 Basic global thresholding, Optimal thresholding using Otsu’s
1 5 1, 2
method
Multi-spectral thresholding, Region based segmentation. 2 5 1, 2
Region growing, Region splitting and Merging. 2 5 1, 2
Unit Color Image Processing,
9
4 Image Compression
Colour image processing: Fundamentals, motivation, full and
2 5 1
pseudo colour image processing
Components of colour, primary and secondary colours,
1 5 1
tristimulus, chromaticity diagram,
Colour models: RGB, CMY, CMYK, HSI 1 5 1, 3
Colour conversion, numerical on colour conversion 1 5 1, 3
Image compression: Motivation, Applications, Compression ratio 1 4 1, 2
Data redundancy- Coding, Inter-pixel and Psycho-visual
1 4 1, 2
redundancy,
JPEG Coding, Huffman Coding 1 4 1, 2
LPZ coding, arithmetic coding, lossless and lossy predictive
1 4 1, 2
coding
Unit
Image representation and Object Recognition 9
5
Image presentation and description- Introduction, Motivations 2 5 3
Shape features (Region-based shape representation and
descriptors) Area, Euler’s number, eccentricity, Elongatedness, 2 5 3
rectangularity, direction, compactness. moments, covex hull.
Texture features, Color features 1 5 3
Object and Pattern Recognition: Pattern and pattern classes. 1 5 3
Matching, classifier role minimum distance or nearest neighbor
1 5 1, 4
classifier.
Matching by correlation, Optimum statistical classifier 1 5 1, 4
Neural network classifier 1 5 1, 4
Total Contact Hours 45

Course Unitization Plan - Lab

Required
S. CLOs References
Experiment Name Contact
No. Addressed Used
Hours 30
Lab Experiment 1:
Perform the following operations using library functions
a. Read, Display and write any color image in other formats. b.
1. Find RED, GREEN and BLUE plane of the color image. c. Convert 2 1 1
color image to grayscale image and binary image
d. Resize the image by one half and one quarter. i.e. Image rotates
by 45, 90 and 180 degrees.
Lab Experiment 2:
Create black and white images (A) of size 1024x1024. Which
consists of alternative horizontal lines of black and white? Each
line is of size 128. Create black and white images (B) of size
1024x1024. Which consists of alternative vertical lines of black and
white? Each line is of size128. Perform the following operations on
2. Image A and Image B. a. Image addition of A and B 2 1 1
b. Subtraction of A and B
c. Multiplying Images of A and B
d. Create a grayscale image of size 256 x 1024. Intensity of image
should vary sinusoidally.
e. Create a white image of size 256x256, with black box of size
58x58 at centre.
3. Lab Experiment 3: 3 2,3 1
 Develop programs for following intensity transformation operation
on a grayscale image. Collect any gray scale image from any
source. Process that image using these operations.
a. Image negative
b. Log transformation and inverse log transform: s = c log (1+r), c
is a const, r ≥ 0. s is pixel intensity of output image, r is the pixel
intensity of input image. Study the effect of constant c on the
quality of output image.
c. Power law transformation: Study the effect of different values of
Gamma used in this transformation.
d. Contrast stretching
e. Gray level slicing
Lab Experiment 4:
Develop programs for following spatial filtering operations on a
grayscale image.
a. Averaging: Implement averaging filtering operations for different
window sizes and study their effect on the quality of output image.
Write your observations on output image quality.
b. Weighted averaging: Implement weighted averaging filtering
operations for different window sizes and study their effect on the
4. 3 4,5 4
quality of output image. Write your observations on output image
quality.
c. Median filtering: Implement weighted averaging filtering
operations for different window sizes and study their effect on the
quality of output image. Write your observations on output image
quality.
d. Max filtering
e. Min filtering
Lab Experiment 5:
Take a grayscale image and add salt and pepper noise. Write
programs for following operations and observe their outputs a.
Linear smoothing or Image averaging
5. b. Weighted averaging 4 2,6 1
c. Median filtering. Compare the output quality among Image
averaging and median filtering.
d. Max filtering
e. Min filtering
Lab Experiment 6:
Write programs to perform following sharpening operations on a
grayscale image
a. Laplacian filter
6. b. Filtering using composite mask 4 2,6 1
c. Unsharp masking
d. High boost filtering
e. Filtering using first order derivative operators such as sobel and
prewitt mask.
Lab Experiment 7:
Write a program to improve contrast of an image using histogram
equalization. The prototype of the function is as below:
7. histogram_equalisation(input_Image, no_of_bins); The function 3 2 1
should return the enhanced image. Consider two low contrast input
images. Study the nature of the output image quality in each case
by varying the number of bins.
Lab Experiment 8:
Take a low contrast grayscale image (A) and a high contrast gray
8. scale image (B). Write a program to improve the contrast of A with 3 2 1
the help of image B using histogram specification or matching. The
prototype of the function is as below: Histogram_sp(input_Image,
 specified_Iage, no_of_bins); The function should return the
enhanced image.
Lab Experiment 9:
Develop programs to implement frequency domain smoothing
filters (Ideal, Butterworth and Gaussian) and apply these filters on a
grayscale image.
a. Compare/comment on the output of Ideal, Butterworth and
Gaussian Low pass Filters having the same radii (cutoff frequency)
9. value. 3 2 1,2,3
b. Consider a suitable gray scale image and demonstrate the ringing
effect on the output of Ideal low pass frequency domain filter.
c. Compare the output of Butterworth low pass filters (order n=2)
for different cutoff frequencies (5, 15, 30, 90, 120).
d. Compare the output of Gaussian low pass filters for different cut-
off frequencies (5, 15, 30, 90, and 120).
Lab Experiment 10:
Develop programs to implement frequency domain
sharpening/High pass filters (Ideal, Butterworth and Gaussian) and
apply these filters on a grayscale image.
a. Compare/comment on the output of Ideal, Butterworth and
Gaussian High pass Filters having the same radii (cutoff frequency)
10. value. 3 2 1,2,3
b. Consider a suitable gray scale image and demonstrate the ringing
effect on the output of Ideal high pass frequency domain filter.
c. Compare the output of Butterworth high pass filters (order n=2)
for different cut-off frequencies (5, 15, 30, 90, 120).
d. Compare the output of Gaussian high pass filters for different
cut-off frequencies (5, 15, 30, 90, and 120).
Total Contact Hours 30

Learning Assessment
Continuous Learning Assessments (50%) End Semester Exam
Bloom’s Level of (50%)
Practical
Cognitive Task CLA-1 CLA2 CLA-3 Mid Th Prac
(20%)
(5%) (5%) (5%) (15%) (30%) (20%)
Remember
Level 1 70% 50% 40% 40% 20% 40% 30%
Understand
Apply
Level 2 30% 50% 60% 40% 30% 40% 30%
Analyse
Evaluate
Level 3 20% 50% 20% 40%
Create
Total 100% 100% 100% 100% 100% 100% 100%

Recommended Resources
1. Gonzalez, R. C. (2009). Digital image processing. Pearson education India.
2. Sridhar, S. (2016) Digital Image Processing, Oxford University Press.
3. Sonka, M., Hlavac, V., & Boyle, R. (2013). Image processing, analysis and machine vision. Springer.
4. Forsyth, D. A., & Ponce, J. (2002). Computer vision: a modern approach. prentice hall professional technical reference.

Other Resources
1. No Data

Course Designers
1. No Data
 SRM University AP, Andhra Pradesh
Neerukonda, Mangalagiri Mandal,
Guntur District, Mangalagiri, Andhra Pradesh – 522240.

Deep Learning
L T P C
Course Code CSE 457 Course Category Stream Elective (SE)
3 0 1 4
Pre-Requisite Progressive
Co-Requisite Course(s) NIL NIL
Course(s) Course(s)
Course Offering Professional / Licensing
CSE
Department Standards

Course Objectives / Course Learning Rationales (CLRs)

1. Understand the fundamental concepts of ML/DL, tensor flow, and keras
2. Study of different activation functions and ANN.
3. Study and application of CNN, and RNN models
4. Application of different deep learning concepts.

Course Outcomes / Course Learning Outcomes (CLOs)

Expected Expected
Bloom’s
At the end of the course the learner will be able to Proficiency Attainment
Level
Percentage Percentage
Outcome 1 Illustrate the concepts of ML/DL 1 70 68
Outcome 2 Design and implement CNN model 2 70 65
Outcome 3 Design and implement RNN model 2 70 65
Outcome 4 Apply deep learning models to given problems. 3 70 60

Course Articulation Matrix (CLO) to Program Learning Outcomes (PLO)

Program Learning Outcomes (PLO)

Project Management
Analysis, Design and

Multicultural Skills

Life Long Learning

Moral, and Ethical
Environment and

Self-Directed and
Modern Tool and

Teamwork Skills

Communication
Individual and
Sustainability
Development

and Finance
Engineering

Society and
Knowledge

Design and

Awareness
CT Usage
Research
Problem

CLOs
Analysis

PSO 1

PSO 2

PSO 3
Skills

Outcome 1 1 1 1 1 2 2 2

Outcome 2 2 2 3 2 3 3 2

Outcome 3 2 2 3 2 3 2 3

Outcome 4 2 2 3 3 3 2 3

Average 2 2 3 2 3 2 3
Course Unitization Plan Theory
Unit No. Unit Name Required CLOs References
Contact Hours Addressed Used
Unit 1 Introduction: 11
Overview of machine learning 2 1 1
History of Deep Learning 1 1 1
Introduction to TensorFlow: 1 1 1
Computational Graph, Key highlights, Creating a Graph 1 1 1
Linear classifiers, loss functions , Regression example 1 1 1
Gradient Descent 1 1 1
TensorBoard 2 1 1
Modularity, Sharing Variables 1 1 1
Keras 1 4 3

Unit 2 ACTIVATION FUNCTIONS , PERCEPTRON, ANN 9

Activation Functions: Sigmoid, ReLU, Hyperbolic Fns, 2 1 1,2
Softmax

Perceptrons: What is a Perceptron, XOR Gate 1 1 1

Artificial Neural Networks: Introduction 1 1 2
Perceptron Training Rule 2 1 2
Gradient Descent Rule 2 1 2
Vanishing gradient problem and solution 1 1 2
Unit 3 Convolutional Neural Networks 8
Introduction to CNNs 2 1,2 3
Kernel filter 1 1,2 3
Principles behind CNNs 1 1,2 3
Long Short-Term Memory (LSTM) 2 1,2 3
Problem and solution of under fitting and overfitting 2 1,2 3
Unit 4 Recurrent Neural Networks 8
Introduction to RNNs 2 1,3 2
Unfolded RNNs 1 1,3 2
Seq2Seq RNNs 1 1,3 2
LSTM 1 1,3 2
GRU 1 1,3 2
Encoder Decoder architectures 2 1,3 2
Unit 5 Deep Learning applications 9
Image segmentation 1 4 3
Self-Driving Cars 1 4 3
News Aggregation and Fraud News Detection 1 4 3
Natural Language Processing 1 4 3
Virtual Assistants 1 4 3
Entertainment 1 4 3
Visual Recognition 1 4 3
Fraud Detection, Healthcare 2 4 3
Total Contact Hours 45
Course Unitization Plan Lab

Required CLOs References

Unit Name
Contact Hours Addressed Used
Lab 1: To implement a Multilayer Perceptron
(MLP) using Keras with TensorFlow, and fine-
3 1,2 1
tune neural network hyperparameters for
regression problem (house price prediction).
Lab 2: To implement a MLP using Keras with
TensorFlow for classification problem (heart 3 1,2,3 1
disease prediction).
Lab 3: To implement a Convolution Neural
Network (CNN) for dog/cat classification problem 3 2,3 1
using TensorFlow/Keras.
Lab 4: To implement a CNN for handwritten digit
2 1,2,3 1
recognition.
Lab 5: To Implement a CNN for object detection
3 2,3 1
in the given image.
Lab 6: To implement a Long Short-Term Memory
3 3,4
(LSTM) for predicting time series data.
Lab 7: To implement a Seq2Seq Model for Neural
3 3,4 1
Machine Translation.
Lab 8: To implement a Recurrent Neural Network
3 3,4 1
(RNN) for predicting time series data.
Lab 9: To implement an Encoder-Decoder
Recurrent neural network model for Neural
3 2,3,4 1
Machine Translation.

Lab 10: Case Study 1: Object detection for Self-

3 1,2,3,4 1,2
Driving Cars
Lab 11: Case Study 2: Object detection for
3 1,2,3,4 1,2
Healthcare images
Total 30
Learning Assessment
Continuous Learning Assessments (50%) End Semester
Bloom’s Level of CLA-1 Mid-1 (15%) CLA-2 CLA-3 Exam (50%)
Cognitive Task Th Th Th Prac Th Prac
Prac Th Prac Prac
(5%) (5%) (10%) (15%) (35%) (15%)
Remember
Level 1 40% 40% 20% 10% 10% 10% 10%
Understand
Apply
Level 2 30% 30% 40% 50% 40% 40% 40%
Analyse
Evaluate
Level 3 30% 30% 40% 40% 50% 50% 50%
Create
Total 100% 100% 100% 100% 100% 100% 100%

Recommended Resources
1. Buduma, N., Buduma, N., & Papa, J. (2022). Fundamentals of deep learning, 2nd ed. O'Reilly Media, Inc."
2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning, 2nd ed. MIT press.

Other Resources
1. https://www.youtube.com/watch?v=aPfkYu_qiF4&list=PLyqSpQzTE6M9gCgajvQbc68Hk_JKGBAYT
2. https://www.coursera.org/professional-certificates/tensorflow

Course Designers
1. No Data
 SRM University AP, Andhra Pradesh
Neerukonda, Mangalagiri Mandal,
Guntur District, Mangalagiri, Andhra Pradesh – 522240.

Principles of Soft Computing

L T P C
Course Code CSE 458 Course Category Stream Electives (SE)
3 0 1 4
Pre-Requisite Progressive
CSE 201, CSE 336 Co-Requisite Course(s)
Course(s) Course(s)
Course Offering Professional / Licensing
CSE
Department Standards

Course Objectives / Course Learning Rationales (CLRs)

1. Understand the fundamental theory and concepts of neural networks, Identify different neural network architectures,
algorithms, applications and their limitations.
2. Understand appropriate learning rules for each of the architectures and learn several neural network paradigms and its
applications.
3. Comprehend the fuzzy logic and the concept of fuzziness involved in various systems and fuzzy set theory.
4. Understand the concepts of fuzzy sets, knowledge representation using fuzzy rules, approximate reasoning, fuzzy
inference systems, and fuzzy logic.
5. Understand the Genetic Algorithm and able to identify the application area.
6. Understand soft computing techniques and their role in problem solving.Reveal different applications of these models to
solve engineering and other problems.

Course Outcomes / Course Learning Outcomes (CLOs)

Expected Expected
Bloom’s
At the end of the course the learner will be able to Proficiency Attainment
Level
Percentage Percentage
Outcome 1 Demonstrate neural network model 3 90% 75%
Describe neural network architectures, algorithms, applications and
Outcome 2 2 70% 65%
their limitations
Apply fuzzy logic and reasoning to handle uncertainty and solve
Outcome 3 3 80% 75%
engineering problems
Outcome 4 Apply genetic algorithms to combinatorial optimization problems 3 80% 75%
Evaluate and compare solutions by genetic algorithms with
Outcome 5 5 65% 60%
traditional approaches for a given problem.

Course Articulation Matrix (CLO) to Program Learning Outcomes (PLO)

Program Learning Outcomes (PLO)

Project Management
Analysis, Design and

Multicultural Skills

Life Long Learning

Moral, and Ethical
Environment and

Self-Directed and
Modern Tool and

Teamwork Skills

Communication
Individual and
Sustainability
Development

and Finance
Engineering

Society and
Knowledge

Design and

Awareness
CT Usage
Research

CLOs
Problem
Analysis

PSO 1

PSO 2

PSO 3
Skills

Outcome 1 3 1 2 1 2 1 1 2 3 2 1 3 3 2 1
Outcome 2 3 2 1 2 2 2 2 2 3 3 2 3 3 2 1
Outcome 3 3 3 3 2 2 2 2 2 3 3 2 3 3 2 2
Outcome 4 3 3 3 2 3 2 2 2 3 3 2 3 3 3 2
Outcome 5 3 3 3 3 3 3 2 2 3 3 3 3 3 3 3
Average 3 2 2 2 2 2 2 2 3 3 2 3 3 2 2
Course Unitization Plan Theory
Required
CLOs References
Unit No. Unit Name Contact
Addressed Used
Hours
Unit I Introduction to Soft Computing, ANN 9
Introduction to Soft Computing, Artificial Neural Network (ANN)
1 1 1

Fundamentals of ANN, Basic Models of an artificial Neuron,

1 1,2 1
Neural Network Architecture
Learning methods, Terminologies of ANN 1 1 1,3
Hebb network 1 2 1,3
Supervised Learning Networks: Perceptron, Adaline, Madaline 1 1 1
Multi-Layer Perceptron 1 1,2 1
Feed forward Back propagation Network 1 1,2 1
Back propagation learning 1 1,2 1
Learning Effect of Tuning parameters of the Back propagation 1 2,5 1
Unit II Advanced Neural Network 9
RBF Network, Associative memory: 1 2 1,3
Auto, hetero and linear associative memory network 1 2 1,3
Adaptive Resonance Theory: ART1 1 2 1,3
ART2 1 2 1,3
Introduction to Computer vision 1 2 1,3
Introduction to Convolutional Neural Network 1 2 1,3
Popular architectures: AlexNet 1 2,5 1,3
GoogleNet 1 2,5 1,3
VGG Net 1 2,5 1,3
Unit III Fuzzy Logic 9
FUZZY LOGIC : Fuzzy set theory: 1 3 2
Crisp sets, fuzzy sets 1 3 2
Crisp relations, fuzzy relations 1 3 2
Fuzzy Systems 1 3 2,3
Crisp logic, predicate logic 1 3 2,3
Fuzzy logic 1 3 2,3
fuzzy Rule based system 1 3,5 2,3
Defuzzification Methods 1 3 2,3
Fuzzy rule-based reasoning 1 3,5 2,3
Unit IV Genetic Algorithms 9
Genetic Algorithms: Fundamentals of genetic algorithms: 1 4 3
Encoding, Fitness functions, Reproduction. 1 4 3
Genetic Modeling : Cross cover, Inversion and deletion 1 4 3
Mutation operator, Bit-wise operators, Bitwise operators used in
1 4 3
GA.
Convergence of Genetic algorithm. 1 4 3
Applications of Genetic Algorithms 1 4,5 3
Real life Problems of Genetic Algorithms 1 5 3
Particle Swarm Optimization 1 4,5 3
Variants of PSO 1 4 3
Unit V Advanced Soft Computing 9
Hybrid Soft Computing Techniques Hybrid system 1 4 2,3
Advanced neural Networks 1 2 1,3
Fuzzy logic and Genetic algorithms hybrids. 1 3,4 2,3
Genetic Algorithm based Back propagation Networks 1 1,4 2,3
GA based weight determination applications 1 4,5 2,3
Fuzzy logic controlled genetic Algorithms 1 3,4 2,3
Soft computing tools 1 5 3
Soft computing Applications 2 5 3
 Total contact hours 45

Course Unitization Plan - Lab

Required
Unit CLOs References
Experiment Name Contact
No. Addressed Used
Hours
Introduction to Soft Computing and ANN
Write a Python Program to implement a perceptron. The input is
1 1 1,3
your semester marks.
Write a python program to extend the exercise given above to
implement Feed Forward Network. The inbuilt function should not 2 1,2 1,3
be used.
Write a python program to implement Hebb Network. The inbuilt
2 1,2 1,3
function should not be used.
Unit I Write a python program to implement Multilayer Perceptron. The
2 2 1,3
inbuilt function should not be used.
Write a python program to implement any ANN with back
2 1,2 1,3
propagation learning Algorithm.
Advanced Neural Network
Write a Python Program to implement ART1 and ART 2. 2 2 1,3
Write a python program to implement CNN. 2 2 1,3
Unit
Write a python Programming to realize the working principles of
II 2 2 1,3
popular architectures such as AlexNet, GoogleNet and VGG Net.
Fuzzy Logic
Write python Program to realize Fuzzy Sets arithmetic. 2 2 2,3
Write a python Program to realize fuzzy relations. 1 2 2,3
Write a python program to realize a fuzzy rule of any popular
2 3 2,3
problem (s).
Unit
Write a python program to realize a defuzzification scheme for the
III 2 3 2,3
above exercise.
Write a python Program to reason the fuzzy rules in exercises 12
2 3 2,3
and 13.
Genetic Algorithms
Write a python program to realize various steps of Genetic
2 4 3
Algorithms.
Unit
Write a Python Program to realize GA based back propagation
IV 2 4,5 3
Networks.
Advanced Soft Computing
Unit Write a Python Program to realize Fuzzy Controlled Genetic
2 4,5 1,3
V Algorithms.
Total contact hours 30
Learning Assessment
Continuous Learning Assessments (50%) End Semester Exam
Bloom’s Level of (50%)
Practical
Cognitive Task CLA-1 CLA2 CLA-3 Mid Th Prac
(20%)
(5%) (5%) (5%) (15%) (30%) (20%)
Remember
Level 1 70% 50% 40% 40% 20% 40% 30%
Understand
Apply
Level 2 30% 50% 60% 40% 30% 40% 30%
Analyse
Evaluate
Level 3 20% 50% 20% 40%
Create
Total 100% 100% 100% 100% 100% 100% 100%

Recommended Resources
1. Sivanandan, S. N. and Deepa, S. N. (2011). Principles of Soft Computing Willey India, 2nd Edition.
2. Jang, J. S. R. (1997). Neuro-Fuzzy and Soft Computing/J.-SR Jang, C.-T. Sun, E. Mizutani. A Compute. Approach to Learn.
Mach. Intell. Saddle River, NJ Prentice Hall, Inc.
3. Rajasekaran, S., & Pai, G. V. (2003). Neural networks, fuzzy logic and genetic algorithm: synthesis and applications (with
cd). PHI Learning Pvt. Ltd..

Other Resources
1. No Data

Course Designers
1. No Data