Faculty of Science and Technology

Savitribai Phule Pune University

Maharashtra, India

http://unipune.ac.in

Honours* in Artificial Intelligence and

Machine Learning
Board of Studies
( Computer Engineering)
(with effect from A.Y. 2020-21)
 Savitribai Phule Pune University

Honours* in Artificial Intelligence and Machine Learning

With effect from 2020-21
Course Course Title Teaching Examination Scheme Credit Scheme
Code Scheme and Marks
Year & Semester

Hours /
Week

Presentation
Mid-Semester
End-Semester

Total Marks

Total Credit
Term work
Practical
Theory
Tutorial

Practical

Practical
Theory /
Tutorial
TE 310301 Computational 04 -- -- 30 70 -- -- -- 100 04 -- 04
& Statistics
V
310302 Computational -- -- 02 -- -- 50 -- -- 50 -- 01 01
Programming
Laboratory
Total 04 - 02 100 50 - - 150 04 01 05
Total Credits =05
TE 310303 Artificial Intelligence 04 -- -- 30 70 -- -- -- 100 04 -- 04
&
Total 04 - - 100 - - - 100 04 - 04
VI
Total Credits =04
BE 410301 Machine 04 -- -- 30 70 -- -- -- 100 04 -- 04
& Learning
VII
410302 Machine Learning -- -- 02 -- -- 50 -- -- 50 -- 01 01
Laboratory
Total 04 - 02 100 50 - - 150 04 01 05
Total Credits =05
BE 410303 Soft Computing and 04 - -- 30 70 -- -- -- 100 04 -- 04
& Deep Learning
VIII 410304 Seminar -- 02 -- -- -- - -- 50 50 02 -- 02
Total 04 - 02 100 - -- 50 150 06 - 06

Total Credits =06

Total Credit for Semester V+VI+VII+VIII = 20

* To be offered as Honours for Major Disciplines as–

1. Computer Engineering
2. Electronics and Telecommunication Engineering
3. Electronics Engineering
4. Information Technology

For any other Major Disciplines which is not mentioned above, it may be offered as Minor
Degree.

Reference: https://www.aicte-india.org/sites/default/files/APH%202020_21.pdf / page 99-100

 Savitribai Phule Pune University
Honours* in Artificial Intelligence and Machine Learning
Third Year of Engineering (Semester V)
310301: Computational Statistics
Teaching Scheme Credit Scheme Examination Scheme and Marks
Lecture: 04 Mid_Semester(TH): 30 Marks
04 Hours/Week End_Semester(TH): 70 Marks

Companion Course : Computational Statistics Laboratory

Course Objectives:
To introduce several statistical techniques found to be serving as tools even today in the
development of machine learning and artificial intelligence based computer algorithms.
 To imbibe strong foundation of statistics in students for implementation in computation.
 To understand modern computational methods used in statistics.
 To get detailed approach of simulation, estimation and visualization of statistical data
 To understand the role of computation as a tool of discovery in data analysis.
 To be able to appropriately apply computational methodologies to real world statistical
problems.
 To learn the data processing techniques required to get applied on machine learning
algorithms.
Course Outcomes:
On completion of the course, learner will be able to–
 Identify the suitable method of statistics on the given data to solve the problem of any
heuristic approach of prediction.
 Apply appropriate statistical concepts and skills to solve problems in both familiar and
unfamiliar situations including those in real-life contexts.
 Design and analyze real world engineering problems by applying various statistical
modeling techniques.
 Formulate suitable statistical method required as pre-processing technique for finding the
solution of machine learning algorithm.
 Model and solve computing problem using correlation, and resampling using appropriate
statistics algorithms.
#Exemplar/Case Studies- Elaborated examples/Case Studies are included at the end of each
unit to explore how the learned topics apply to real world situations and need to be explored
so as to assist students to increase their competencies, inculcating the specific skills, building
the knowledge to be applicable in any given situation along with an articulation. One or two
sample exemplars or case studies are included for each unit; instructor may extend the same
with more. Exemplar/Case Studies may be assigned as self-study by students and to be
excluded from theory examinations.
Course Contents
Unit I Introduction to Statistics (07 Hours)
What is statistics, Statistical Data- Categorical, Numerical (Continuous), Univariate and
Bivariate Analysis, Mean, Median, Mode, Standard Deviation, Harmonic Mean, Data
Visualization-Line, Scatter, Box plots, Histogram, Statistical Thinking.
#Exemplar/ Case Studies Know about the great statistician- Ronald Fisher
Unit II Distributions (9 Hours)
Probability Distributions, Characterizing a Distribution, Discrete Distributions, Normal
Distributions, Continuous Distributions Derived from the Normal Distribution, Poisson
Distribution, Other Continuous distributions- Lognormal, Weighbull, Exponential, Uniform.

#Exemplar/ Case Studies Know about the great statistician and father of Indian statistical
institute- Praful Chandra Mahanalobis
Unit III Hypothesis Tests and Statistical Tests (08 Hours)
Typical Analysis procedures, Hypothesis Concept, Errors, p-Value, and Sample Size, Confusion
Matrix, Sensitivity and Specificity, ROC-AUC Curve, Test on Numerical Data- Distribution of a
Sample Mean, Comparison of Two Groups, Comparison of Multiple Groups
#Exemplar/ Case Studies Study brief history of Statistics
Unit IV Statistical Methods (08 Hours)
Standard Deviation, Normalization- Feature Scaling, Min-Max scaling, Bias, Variance,
Regularization, Ridge Regression, Lasso Regression, Cross Validation Techniques- K-fold,
LOOCV, Stratified K-fold, Grid Search CV, CV Error
#Exemplar/ Case Studies Euclid’s Elements
Unit V Statistical Processing (08 Hours)
Dimensionality Reduction Techniques- Principal Component Analysis, Discriminant Analysis,
Feature Selection- Chi2 square method, Variance Threshold, Recursive Feature Elimination,
Outliers detection methods, Resampling-Random, under-sampling and over re-sampling
#Exemplar/ Case Studies Study about Anomalies
Unit VI Statistical Modeling (08 Hours)
Linear Regression models, Correlation coefficient, Rank Correlation, Residual Error, Mean
Square Error, RMSE, Multilinear Regression, Polynomial Features, Gradient Descent, Logistic
Regression, Bayesian Statistics, Bayes’ Theorem, Monte Carlo Method
#Exemplar/ Case Studies Study Biography of Thomas Bayes
Learning Resources
Text Books:
 Thomas Haslwanter, "An Introduction to Statistics with Python with Applications in the
Life Sciences", Springer International Publishing Switzerland 2016, ISBN 978-3-319-
28315-9, ISBN 978-3-319-28316-6 (eBook)
 Allen B. Downey, "Think Stats", Second Edition, O’Reilly Media, ISBN: 978-1-491-
90733-7
Reference Books:
 Thomas Haslwanter, "An Introduction to Statistics with Python with Applications in the
Life Sciences", Springer International Publishing Switzerland 2016, ISBN 978-3-319-
28315-9, ISBN 978-3-319-28316-6 (eBook)
 Peter Bruce and Andrew Bruce, "Practical Statistics for Data Scientists", First Edition,
O’Reilly Media, ISBN-978-1-491-95296-2
 Allen B. Downey, "Think Stats", Second Edition, O’Reilly Media, ISBN: 978-1-491-
90733-7
 José Unpingco, "Python for Probability, Statistics, and Machine Learning", Springer
International Publishing Switzerland, ISBN 978-3-319-30715-2, DOI 10.1007/978-3-
319-30717-6, ISBN 978-3-319-30717-6 (eBook)
 Claus Weihs, Olaf Mersmann, Uwe Ligges, "Foundations of Statistical Algorithms", CRC
Press, ISBN-978-1-4398-7887-3 (eBook - PDF)
e-Books:
 http://file.allitebooks.com/20151204/Foundations%20of%20Statistical%20Algorithms.
pdf
 http://onlinestatbook.com/Online_Statistics_Education.pdf
 https://upload.wikimedia.org/wikipedia/commons/8/82/Statistics.pdf
 http://cnx.org/content/col10522/1.38/pdf
 http://www.greenteapress.com/thinkstats/thinkstats.pdf
MOOC/ Video Lectures available at:
 https://www.udemy.com/course/introduction-to-bayesian-statistics/ (Free Course)
 https://www.udacity.com/course/intro-to-statistics--st101# (Free Course)
 https://nptel.ac.in/courses/111/105/111105090/
 https://nptel.ac.in/courses/111/105/111105077/
 Savitribai Phule Pune University
Honours* in Artificial Intelligence and Machine Learning
Third Year of Engineering (Semester V)
310302: Computational Programming Laboratory
Teaching Scheme Credit Scheme Examination Scheme and Marks
Practical:2 Hours/Week 01 Term work:50 Marks

Guidelines for Laboratory Conduction

 Lab Assignments: Following is list of suggested laboratory assignments for reference.
Laboratory Instructors may design suitable set of assignments for respective course at their
level. Beyond curriculum assignments and mini-project may be included as a part of
laboratory work. The instructor may set multiple sets of assignments and distribute
among batches of students. It is appreciated if the assignments are based on real world
problems/applications. The Inclusion of few optional assignments that are intricate and/or
beyond the scope of curriculum will surely be the value addition for the students and it will
satisfy the intellectuals within the group of the learners and will add to the perspective of
the learners. For each laboratory assignment, it is essential for students to
draw/write/generate flowchart, algorithm, test cases, mathematical model, Test data set and
comparative/complexity analysis (as applicable). Batch size for practical and tutorial may
be as per guidelines of authority.
 Term Work–Term work is continuous assessment that evaluates a student's progress
throughout the semester. Term work assessment criteria specify the standards that must
be met and the evidence that will be gathered to demonstrate the achievement of course
outcomes. Categorical assessment criteria for the term work should establish
unambiguous standards of achievement for each course outcome. They should describe
what the learner is expected to perform in the laboratories or on the fields to show that
the course outcomes have been achieved. It is recommended to conduct internal
monthly practical examination as part of continuous assessment.
 Assessment: Students’ work will be evaluated typically based on the criteria like
attentiveness, proficiency in execution of the task, regularity, punctuality, use of
referencing, accuracy of language, use of supporting evidence in drawing conclusions,
quality of critical thinking and similar performance measuring criteria.
 Laboratory Journal- Program codes with sample output of all performed assignments are
to be submitted as softcopy. Use of DVD or similar media containing students programs
maintained by Laboratory In-charge is highly encouraged. For reference one or two
journals may be maintained with program prints in the Laboratory. As a conscious effort
and little contribution towards Green IT and environment awareness, attaching printed
papers as part of write-ups and program listing to journal may be avoided. Submission of
journal/ term work in the form of softcopy is desirable and appreciated.

Suggested list of assignments

(Use suitable programming language/Tool for implementation)
Sr. Assignment statement
1 Compute Estimators of the main statistical measures like Mean, Variance, Standard
Deviation, Covariance, Correlation and Standard error with respect to any example.
Display graphically the distribution of samples.
2 Plot the Normal Distribution for class test result of a particular subject. Identify the
Skewness and Kurtosis
3 Load the dataset: birthwt Risk Factors Associated with Low Infant Birth Weight at
https://raw.github.com/neurospin/pystatsml/master/datasets/birthwt.csv
1. Test the association of mother’s (bwt) age and birth weight using the correlation
test and linear regeression.
2. Test the association of mother’s weight (lwt) and birth weight using the
correlation testand linear regeression.
3. Produce two scatter plot of: (i) age by birth weight; (ii) mother’s weight by birth
weight. Elaborate the Conclusion
4 Apply Basic PCA on the iris dataset. The data set is available at:
https://raw.github.com/neurospin/pystatsml/master/datasets/iris.csv
• Describe the data set. Should the dataset been standardized?
• Describe the structure of correlations among variables.
• Compute a PCA with the maximum number of components
.• Compute the cumulative explained variance ratio. Determine the number of
components𝐾by your computed values.
• Print the𝐾principal components directions and correlations of the𝐾principal
compo-nents with the original variables. Interpret the contribution of the original
variables into the PC.
• Plot the samples projected into the𝐾first PCs.
• Color samples by their species.
5 Perform clustering of the iris dataset based on all variables using Gaussian mixture
models. Use PCA to visualize clusters.
 Savitribai Phule Pune University
Honours* in Artificial Intelligence and Machine Learning
Third Year of Engineering (Semester VI)
310303: Artificial Intelligence
Teaching Scheme Credit Scheme Examination Scheme and Marks
Lecture: 04 Hours/Week 04 Mid_Semester(TH): 30 Marks
End_Semester(TH): 70 Marks
Prerequisite: Discrete Mathematics, Any Programming Knowledge (Python/Matlab/Java), Machine
Learning.

Companion Course : ---

Course Objectives:
The basic objectives of this course is
• To understand the basic concept of AI, strength and weakness of problem solving
and search
• To study about various heuristic and game search algorithms
• To know about basic concepts of knowledge and reasoning, NLP and Machine
Learning
• To know about various Expert System tools and applications
• To know expert system tools and applications

Course Outcomes:
On completion of the course, learner will be able to–
 Evaluate Artificial Intelligence (AI) methods and describe their foundations.
 Analyze and illustrate how search algorithms play vital role in problem solving, inference,
perception, knowledge representation and learning
 Demonstrate knowledge of reasoning and knowledge representation for solving real world
problems
 Illustrate the construction of learning and expert system
 Discuss current scope and limitations of AI and societal implications.

Course Contents
Unit I Introduction to AI (08 Hours)
Definitions – Foundation and History of AI, Evolution of AI - Applications of AI, Classification of AI
systems with respect to environment. Artificial Intelligence vs Machine learning, Statistical Analysis:
Relationship between attributes: Covariance, Correlation Coefficient, Chi Square. Intelligent Agent:
Concept of Rationality, nature of environment, structure of agents.

Unit II Problem Solving (08 Hours)

Heuristic Search Techniques: Generate-and-Test; Hill Climbing; Properties of A* algorithm, Best-
first Search; Problem Reduction. Constraint Satisfaction problem: Interference in CSPs; Back
tracking search for CSPs; Local Search for CSPs; structure of CSP Problem. Beyond Classical
Search: Local search algorithms and optimization problem, local search in continuous spaces,
searching with nondeterministic action and partial observation, online search agent and unknown
environments.

Unit III Knowledge and Reasoning (08 Hours)

Knowledge and Reasoning: Building a Knowledge Base: Propositional logic, first order Logic,
situation calculus. Theorem Proving in First Order Logic, Planning, partial order planning. Uncertain
Knowledge and Reasoning, Probabilities, Bayesian Networks. Probabilistic reasoning over time:
time and uncertainty, hidden Markova models, Kalman filter, dynamic bayesian network, keeping
track of many objects
Unit IV Learning (07 Hours)
Learning from examples: Overview of different forms of learning, Supervised learning,
Unsupervised learning, Learning Decision Trees, regression and classification with linear model,
SVM, Ensemble learning, Reinforcement learning. Artificial neural network
Unit V Game (06 Hours)
Search under adversarial circumstances. Optimal decision in game, minimax algorithm, alpha-beta
pruning, games with an element of chance, imperfect real time decision, stochastic games, partially
observable games, stat of art game program, alternative approaches
Unit VI Expert Systems (06 Hours)
Introduction to Expert Systems- Inference - Forward chaining - Backward chaining - Languages
and tools - Explanation facilities - Knowledge acquisition. Applications: Natural Language
Processing: General framework for text processing. Case Study: Sentiment Analysis. Computer
Vision: General framework for CV application. Case Study: Object Recognition

.
Learning Resources
Text Books:
• Russell, S. and Norvig, P. 2015. Artificial Intelligence - A Modern Approach, 3rd edition,
Prentice Hall
• J. Gabriel, Artificial Intelligence: Artificial Intelligence for Humans (Artificial Intelligence,
Machine Learning), Create Space Independent Publishing Platform, First edition , 2016

Reference Books:
• Introduction to Artificial Intelligence & Expert Systems, Dan W Patterson, PHI.,2010 2. S
Kaushik, Artificial Intelligence, Cengage Learning, 1st ed.2011
• Ric, E., Knight, K and Shankar, B. 2009. Artificial Intelligence, 3rd edition, Tata McGraw
Hill.
• Luger, G.F. 2008. Artificial Intelligence -Structures and Strategies for Complex Problem
Solving, 6th edition, Pearson
• Alpaydin, E. 2010. Introduction to Machine Learning. 2nd edition, MIT.
 Savitribai Phule Pune University
Honors* in Artificial Intelligence and Machine Learning
Fourth Year of Engineering (Semester VII)
410301: Machine Learning
Teaching Scheme Credit Scheme Examination Scheme and Marks
Lecture: 04 Hours/Week 04 Mid_Semester(TH): 30 Marks
End_Semester(TH): 70 Marks
Prerequisites: Mathematics/Statistics
Companion Course : ---
Course Objectives:
• To understand the basic concepts machine Learning and apply different
dimensionality reduction techniques
• To optimize the different linear methods of regression and classification
• To interpret the different supervised classification methods of support vector
machine and tree based models
• To learn the different models of neural network for solving non linear functions
• To acquire the knowledge of different generative models through unsupervised
learning
• To explain the different graphical and Hidden Markov models of learning

Course Outcomes:
By the end of the course, students will be able to:

• CO1: Recognize the characteristics of machine learning that makes it useful to real-
world problems and apply different dimensionality reduction techniques. L2
• CO2: Use different linear methods for regression and classification with their
optimization through different regularization techniques. L3
• CO3: Apply the different supervised learning methods of support vector machine
and tree based models. L3
• CO4: Select the appropriate type of neural network architecture and apply for
learning non-linear functions. L5
• CO5: Distinguish different generative models through unsupervised learning . L4
• CO6: Draw the inferences from the different graphical and hidden Markov models.
L4
Course Contents
Unit I Introduction (08 Hours)
Introduction to Machine Learning, Examples of Machine Learning Applications, Learning
Types

Supervised Learning -Learning a Class from Examples, Vapnik-Chervonenkis (VC) Dimension,

Probably Approximately Correct (PAC) Learning,Noise, Learning Multiple Classes,
Regression, Model Selection and Generalization, Dimensions of a Supervised Machine
Learning Algorithm

Dimensionality Reduction- Introduction,Subset Selection, Principal Components Analysis,

Factor Analysis, Multidimensional Scaling, Linear Discriminant Analysis,Isomap, Locally
Linear Embedding

Unit II Linear Methods for Regression (08 Hours)

Introduction, Linear Regression Models and Least Squares, Subset Selection, Shrinkage
Methods-Ridge Regression, Lasso Regression, Least Angle Regression, Methods Using
Derived Input Directions-Principal Components Regression, Partial Least Squares, A
Comparison of the Selection and Shrinkage Methods , Multiple Outcome Shrinkage and
Selection, More on the Lasso and Related Path Algorithms, Logistic Regression-Fitting
Logistic Regression Models, Quadratic Approximations and Inference, L1 Regularized
Logistic Regression
Unit III Support Vector Machines and Tree-Based (08 Hours)
Models

SVM-Introduction to SVM, The Support Vector Classifier, Support Vector Machines and
Kernels- Computing the SVM for Classification, The SVM as a Penalization Method, Function
Estimation and Reproducing Kernels, SVMs and the Curse of Dimensionality, A Path
Algorithm for the SVM Classifier, Support Vector Machines for Regression, Regression and
Kernels

Tree Based Methods-Regression Trees, Classification Trees, Random Forests- Definition of

Random Forests, Details of Random Forests- Out of Bag Samples, Variable Importance,
Proximity Plots, Random Forests and Overfitting, Analysis of Random Forests-Variance and
the De-Correlation Effect, Bias, Adaptive Nearest Neighbors
Unit IV Multilayer Perceptrons (08 Hours)

Introduction-Understanding the Brain, Neural Networks as a Paradigm for Parallel

Processing, The Perceptron, Training a Perceptron, Learning Boolean Functions, Multilayer
Perceptrons, MLP as a Universal Approximator ,Backpropagation Algorithm-Nonlinear
Regression,Two-Class Discrimination, Multiclass Discrimination, Multiple Hidden Layers,
Training Procedures-improving Convergence, Overtraining, Structuring the Network,Tuning
the Network Size, Bayesian View of Learning, Dimensionality Reduction, Learning Time-Time
Delay Neural Networks, Recurrent Networks, Regularization in Neural Networks, Bayesian
Neural Networks
Unit V Unsupervised Learning (08 Hours)

Introduction, Association Rules-Market Basket Analysis, The Apriori Algorithm,

Unsupervised as Supervised Learning,Generalized Association Rules, Cluster Analysis-
Proximity Matrices,

Clustering Algorithms-K-mean, Gaussian Mixtures as Soft K-means Clustering, Example:

Human Tumor Microarray Data, Vector Quantization, K-medoids, Hierarchical Clustering,
Self-Organizing Maps, PCA-Spectral Clustering
Unit VI Hidden Markov and Graphical Models (08 Hours)

Hidden Markov Models-Introduction, Discrete Markov Processes,Hidden Markov

Models,Three Basic Problems of HMMs,Evaluation Problem,Finding the State
Sequence,Learning Model Parameters,Continuous Observations,The HMM with
Input,Model Selection in HMM

Graphical Models-Introduction,Canonical Cases for Conditional Independence,Example

Graphical Models-Naive Bayes’ Classifier, Hidden Markov Model,Linear Regression, d-
Separation,Belief Propagation-Chains,Trees,olytrees,Junction Trees, Undirected Graphs:
Markov Random Fields,Learning the Structure of a Graphical Model,Influence Diagrams
Learning Resources
Text Books:
• Introduction to Machine Learning Edition 2, by Ethem Alpaydin
• The Elements of Statistical Learning. Trevor Hastie, Robert Tibshirani and Jerome
Friedman. Second Edition. 2009.
• Machine Learning. Tom Mitchell. First Edition, McGraw- Hill, 1997.

Reference Books:
• Pattern Recognition and Machine Learning. Christopher Bishop. Springer. 2006.
• Understanding Machine Learning. Shai Shalev-Shwartz and Shai Ben-David. Cambridge
University Press. 2017.
• Understanding Machine Learning. Shai Shalev-Shwartz and Shai Ben-David. Cambridge
University Press. 2017.
• Understanding Machine Learning, Shai Shalev-Shwartz and Shai Ben-David, Published
2014 by Cambridge University Press.
e-Books:
• https://web.stanford.edu/~hastie/ElemStatLearn/
• http://www.springer.com/in/book/9780387310732
• http://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/
• https://www.cs.cornell.edu/jeh/book.pdf
MOOC/ Video Lectures available at:
• https://nptel.ac.in/courses/106/106/106106139/
• https://nptel.ac.in/courses/106/106/106106202/
• https://nptel.ac.in/courses/106/106/106106198/
• https://nptel.ac.in/courses/106/105/106105152/
• https://nptel.ac.in/courses/106/106/106106213/
• https://www.coursera.org/learn/machine-learning
 Savitribai Phule Pune University
Honors* in Artificial Intelligence and Machine Learning
Fourth year of Engineering (Semester VII)
410302: Machine learning Laboratory
Teaching Scheme Credit Scheme Examination Scheme and Marks
Practical: 01 Hours/Week 01 Term work: 50 Marks
Guidelines for Laboratory Conduction
 Lab Assignments: Following is list of suggested laboratory assignments for reference. Laboratory
Instructors may design suitable set of assignments for respective course at their level. Beyond
curriculum assignments and mini-project may be included as a part of laboratory work. The
instructor may set multiple sets of assignments and distribute among batches of students. It is
appreciated if the assignments are based on real world problems/applications. The Inclusion of
few optional assignments that are intricate and/or beyond the scope of curriculum will surely be
the value addition for the students and it will satisfy the intellectuals within the group of the
learners and will add to the perspective of the learners. For each laboratory assignment, it is
essential for students to draw/write/generate flowchart, algorithm, test cases, mathematical model,
Test data set and comparative/complexity analysis (as applicable). Batch size for practical and
tutorial may be as per guidelines of authority.
 Term Work–Term work is continuous assessment that evaluates a student's progress throughout
the semester. Term work assessment criteria specify the standards that must be met and the
evidence that will be gathered to demonstrate the achievement of course outcomes. Categorical
assessment criteria for the term work should establish unambiguous standards of achievement
for each course outcome. They should describe what the learner is expected to perform in the
laboratories or on the fields to show that the course outcomes have been achieved. It is
recommended to conduct internal monthly practical examination as part of continuous
assessment.
 Assessment: Students’ work will be evaluated typically based on the criteria like attentiveness,
proficiency in execution of the task, regularity, punctuality, use of referencing, accuracy of
language, use of supporting evidence in drawing conclusions, quality of critical thinking and
similar performance measuring criteria.
 Laboratory Journal- Program codes with sample output of all performed assignments are to be
submitted as softcopy. Use of DVD or similar media containing students programs maintained by
Laboratory In-charge is highly encouraged. For reference one or two journals may be maintained
with program prints in the Laboratory. As a conscious effort and little contribution towards Green
IT and environment awareness, attaching printed papers as part of write-ups and program listing
to journal may be avoided. Submission of journal/ term work in the form of softcopy is desirable
and appreciated.
Sr. No Suggested List of assignment
1 Creating & Visualizing Neural Network for the given data. (Use python)
Note: download dataset using Kaggal. Keras, ANN visualizer, graph viz libraries are
required.
2 Recognize optical character using ANN
3 Implement basic logic gates using Hebbnet neural networks
5 Exploratory analysis on Twitter text data
Perform text pre-processing, Apply Zips and heaps law, Identify topics
4 Text classification for Sentimental analysis using KNN Note: Use twitter data
6 Write a program to recognize a document is positive or negative based on polarity
words using suitable classification method.
 Savitribai Phule Pune University
Honours* in Artificial Intelligence and Machine Learning
Fourth Year of Engineering (Semester VIII)
410303: Soft Computing and Deep Learning
Teaching Scheme Credit Scheme Examination Scheme and Marks
Lecture: 04 Hours/Week 04 Mid_Semester(TH): 30 Marks
End_Semester(TH): 70 Marks
Prerequisites: Knowledge of basic computing techniques
Companion Course : ---
Course Objectives:
The basic objectives of this course is
• To understand different soft computing techniques and its applications.
• To introduce students to understand, explain, and apply the fuzzy set and fuzzy
logic in real life applications
• To understand the use of genetic algorithm to design and develop various
applications
• To understand and acquire knowledge of artificial neural network and its
different learning and computing mechanism
• To study how to model complex problems using deepl learning network.
• To learn and and design a solution by applying the principles of CNN and RNN to
solve diversified complex problem
Course Outcomes:
On completion of the course, learner will be able to–
CO 1: Formulate the real life problem by mapping different soft computing techniques
CO 2: Apply principles of Soft computing to solve problmes in varieties of application
domains.
CO 3: Design and analyze real world engineering problems by applying genetic algorithm
and its basic principles
CO 4: Specify, manipulate and apply CNN and RNN to solve diversified complex real world
problems
CO 5: Calculate the minimum weight of the neural network to find the optimized solution
of a problem
CO6: Model and solve computing problem using artificial neural network, fuzzy systems
and genetic algorithm
Course Contents
Unit I Basics of Soft Computing (06 Hours)
Evolution of Computing, Inroduction of Soft Computing, Hard Computing and Soft
Computing, Requirement of Soft Computing, Charactersetics of Soft Computing, Major
areas of Soft Computing, Applications of Soft Computing.

Unit II Fuzzy Logic (06 Hours)

Fuzzy Set theory, Fuzzy set versus Crisp set, Membership function, Operations on Fuzzy set,
Fuzzy Relation, Fuzzification and Defuzzification, Minmax Composition, Fuzzy Logic, Fuzzy
Rule based systems, Predicate logic, Fuzzy Decision Making, Fuzzy Control Systems, Fuzzy
Classification, Fuzzy controllers, Application of Fuzzy systems(Real life)
Unit III Genetic Algorithm (06 Hours)
Evolution of Genetic Algorithms (GA), Basic GA framework and different GA architectures,
GA operators: Crossover, Selection, Mutation, Fitness function, Convergence Working
Principle, Vncoding methods , Bit wise operation in GA, Multi-level Optimization,
Applications of GA in Machine Learning.
Unit IV Neural Network (06 Hours)
Introduction, Learning rules and activation functions, Single layer and multilayer
Perceptrons , Feed forward and Back propagation networks, Architecture of
Backpropagation (BP) Networks, Backpropagation Learning mechanism, Types of Artificial
Neural Network(ANN), Introduction to Associative Memory, Adaptive Resonance, Self
Organizing Map, Recent applications (real life)
Unit V Deep Learning I (06 Hours)
Introduction, Why to go deep ?, Architecture of Deep Network, Restricted Boltzman Machines, Deep
belief Network, Tensor Flow, Deep Learning libraries, Deep Learning platform, Theano, Caffe, Deep
Learning Use Cases.
Unit VI Deep Learning II (06 Hours)
Introduction to Convolution Neural Network(CNN), Properties of CNN representations: invertibility,
stability, Convolution layers invariance, Residual Nets, Scattering networks, Group formalism,
Applications of CNN.
Introduction to Recurrent Neural Network(RNN), Sequential processing LSTM, Language Modeling,
Image Captioning, Applications of RNN.
Learning Resources
Text Books:
• Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis & Applications,
S.Rajasekaran, G. A. Vijayalakshami, PHI, 2007.
• An Introduction to Genetic Algorithms, Melanie Mitchell, MIT Press, 2000.
• Fuzzy Logic: A Pratical approach, F. Martin, , Mc neill, and Ellen Thro, AP Professional, 2000.
• Soft Computing, D. K. Pratihar, Narosa, 2008
Home
Reference Books:
• Fuzzy Logic with Engineering Applications (3rd Edn.), Timothy J. Ross, Willey, 2010
• Neuro-Fuzzy and soft Computing, J.-S. R. Jang, C.-T. Sun, and E. Mizutani, PHI
Learning, 2009
• Foundations of Neural Networks, Fuzzy Systems, and Knowldge Engineering, Nikola K.
Kasabov, MIT Press, 1998
• Genetic Algorithms In Search, Optimization And Machine Learning, David E. Goldberg,
Pearson Education, 2002
• Neural Networks and Learning Machines, (3rd Edn.), Simon Haykin, PHI Learning, 2011.
e-Resources:
• https://cse.iitkgp.ac.in/~dsamanta/courses/sca/index.html
• http://www.musaliarcollege.com/e-Books/CSE/introduction-to-soft-computing%20(1).pdf
• http://www.deeplearningbook.org/
• http://deeplearning.net/tutorial/deeplearning.pdf
• http://www.dkriesel.com/en/science/neural_networks
MOOC/ Video Lectures available at:
• https://nptel.ac.in/courses/106/105/106105173/
• https://nptel.ac.in/courses/117/105/117105084/
• https://nptel.ac.in/courses/127/105/127105006/
 Savitribai Phule Pune University
Honours* in Artificial Intelligence and Machine Learning
Fourth Year of Engineering (Semester VIII)
410304: Seminar
Teaching Scheme Credit Scheme Examination Scheme and Marks
Practical: 02 02 Presentation: 50 Marks
Hours/Week
Course Objectives:
 To train the student to independently search, identify and study important topics in
computer science.
 To develop skills among students to study and keep themselves up to date of the
technological developments taking place in computer science
 To expose students to the world of research, technology and innovation.
Course Outcomes:
On completion of the course, student will be able to
 To train the student to independently search, identify and study important topics in
computer science.
 To develop skills among students to study and keep themselves up to date of the
technological developments taking place in computer science.
 To expose students to the world of research, technology and innovation
Guidelines for Seminar:
 The department will assign an internal guide under which students shall carry out
Hons. seminar work
 In order to select a topic for Hons. Seminar, the student shall refer to various
resources like books, magazines, scientific papers, journals, the Internet and experts
from industries and research institutes
 The topic selected for Hons. Seminar by the students will be scrutinized and if found
suitable, shall be approved by the internal guide
 Student should also explore the tools and technologies available for implementation of
selected topic. Student should implement/ simulate the seminar work partially/ fully
for enhancing the practical skill set on topic.
 Student shall submit the progress of his/her Hons. Seminar work to the internal guide.
 The student shall prepare a REPORT on the work done on Hons. Seminar and submit it
at the time of presentation.
Evaluation of IT Seminar Work
 During the seminar work, its progress will be monitored, by the internal guide.
 At the end of seminar work, copy of Hons. Seminar Report should be prepared and
submitted to department.
 End Examination shall be based on the Report, technical content and Presentation.
 Guidelines for Assessment: Panel of staff members along with a guide would be
assessing the seminar work based on these parameters-Topic, Contents and
Presentation, implementation, regularity, Punctuality and Timely Completion, Question
and Answers, Report, Paper presentation/Publication, Attendance and Active
Participation.
References:
1. Rebecca Stott, Cordelia Bryan, Tory Young, “Speaking Your Mind: Oral Presentation and
Seminar Skills (Speak-Write Series)”, Longman, ISBN-13: 978-0582382435
2. Johnson-Sheehan, Richard, “Technical Communication”, Longman. ISBN 0-321-11764-6