Required CSF THEORY (TH) in the given courses:

Sr. No. Course Title

1 BSI Islamic Studies and Ethics Engr. Usman Ali

2 BSI Calculus and Analytical Geometry Engr. Arbab Sabour

3 BSI Functional English Engr. Usman Ali

4 Occupational Health and Safety Engr. Arbab Sabour

5 Linear Algebra Engr. Arbab Sabour

6 Pakistan Studies and Global Perspective Engr. Naimat Khan

7 Technical Writing Engr. Usman Ali

8 Complex Variables and Transforms Engr. Naimat Khan

9 Discrete Structures  Engr. Naimat Khan

10 Differential Equations Engr. Hazrat Ali

11 Engineering Project Management Engr. Usman Ali

12 Software Engineering Engr. Wajid Ali

13 Probability and Statistics Engr. Hazrat Ali

14 Artificial Intelligence Engr. Abdul Jabbar

15 Introduction to Block Chain Technology Engr. Abdul Jabbar

16 Machine Learning (Th + Lab) Lab Manual Engr. Wasi ullah

17 Deep Learning Engr. Wajid Ali

18 Cyber Security Engr. Wajid Ali

19 Numerical Analysis Engr. Hazrat Ali

Credit Hours: 3

Course Description
This course aims to present the core fundamentals behind the much talked about field of Deep
Learning. We will delve into selected topics of Deep Learning, from discussing basics of neural
networks, to understanding how CNN and RNN works with common examples and publicly available
datasets. Special highlight of the course is the lecture on Interpretability of Neural Networks which
will help students to understand how to trust a neural network’s recommendation. In the final weeks of
the course, we shall get an introductory exposure to Generative Adversarial Networks and
Reinforcement Learning which will help build the foundation for more advanced courses in Artificial
Intelligence.

Course Objectives
1. To give the understanding of the theoretical basis and key features underlying neural networks and
deep learning
2. To make students comfortable with tools and techniques required in handling large amounts of
datasets.
3. Understand the main fundamentals that drive Deep Learning

Course Outlines
Introduction to Deep learning, Review of Linear classification (Multi-class Support Vector Machines, Soft max)
and Regularization, Gradient Descent & Stochastic Gradient Descent (SGD), Back propagation (Intuitions, back
propagation as flow graph), Introduction to Neural Networks (model of a biological neuron, activation functions,

neural net architecture, representational power, etc.), Building Neural Networks (data preprocessing, loss
functions, weight initialization, regularization, dropout, batch normalization), Learning Neural Networks
(Learning and Evaluation gradient checks, sanity checks), Variants of SGD (momentum, Adagrad/RMSprop,
ADAM), Introduction to Convolutional Neural Networks (CNN) and its components (Convolution and Pooling

Layers), Convolutional Neural Network case studies (AlexNet/ZFNet/VGGNet), Understanding and Visualizing
Convolutional Neural Networks, Convolutional networks for other visual Recognition Tasks (Localization,
Detection, Segmentation, etc.), Transfer Learning and Fine-tuning Convolutional Neural Networks, Introduction
to Natural Language Processing (NLP), Introduction to recurrent networks (RNNs, LSTMS, etc.), Applications
of Recurrent neural networks to different NLP tasks (e.g. sentiment analysis, parsing, NER tagging, etc.),
Introduction to Reinforcement Learning
Books
Text Book

Deep Learning, 1st Edition, Yoshua Bengio, Ian Goodfellow, Aaron Courville, Neural Networks and
deep learning, 1st Edition, Michael A. Nielsen

Reference Book:

Hands-On Machine Learning with Scikit-Learn and Tensor Flow, 1st Edition, Aurélien Géron

Artificial Intelligence
Course Code: CSE-XXX Course title: Artificial Intelligence

Credit Hours: 3

Course Description
This course provides an introduction to the fundamentals of artificial intelligence. It contains a theory
component about the concepts and principles that underlie modern AI algorithms, and a practice
component to relate theoretical principles with practical implementation.

Course Objectives
1. Understand key components in the field of artificial intelligence
2. Implement classical artificial intelligence techniques
3. Analyze artificial intelligence techniques for practical problem solving

Course Outlines
Introduction (Introduction, basic component of AI, Identifying AI systems, branches of AI, etc.); Reasoning and
Knowledge Representation (Introduction to Reasoning and Knowledge Representation, Propositional Logic,
First order Logic); Problem Solving by Searching (Informed searching, Uninformed searching, Local
searching.); Constraint Satisfaction Problems; Adversarial Search (Min-max algorithm, Alpha beta pruning,
Game-playing); Learning (Unsupervised learning, Supervised learning, Reinforcement learning) ;Uncertainty
handling (Uncertainty in AI, Fuzzy logic); Recent trends in AI and applications of AI algorithms (trends, Case
study of AI systems, Analysis of AI systems)

Books
Text Book
 Stuart Russell and Peter Norvig, Artificial Intelligence. A Modern Approach, 3rd edition, Prentice Hall,
Inc., 2010.

Reference Book:

1. Hart, P.E., Stork, D.G. and Duda, R.O., 2001. Pattern classification. John Willey & Sons.
2. Luger, G.F. and Stubblefield, W.A., 2009. AI algorithms, data structures, and idioms in Prolog, Lisp,
and Java. Pearson Addison-Wesley.

Machine Learning
Course Code: CSE-XXX

Credit Hours: 3

Course Description
The course assumes basic knowledge of introductory machine learning, and a good background on
probability and statistics, linear algebra, and optimization methods. We will cover modern topics such
as learning theory, transfer learning, meta-learning, domain adaptation, self-adaptive learning
algorithms, deep learning, Gaussian processes, and kernel methods. Students will read papers from
main conferences in machine learning and will learn to identify novel ideas within the field.

Course Objectives
The course will deepen the student's knowledge of how to build computer systems that learn from
experience.

Course Outlines
Introduction to machine learning and statistical pattern recognition. Supervised learning: Part I (Graphical
models (full Bayes, Naïve Bayes), Decision trees for classification & regression for both categorical & numerical
data, Ensemble methods, Random forests, Boosting (Adaboost and Xgboost), Stacking; Part II (Four
Components of Machine Learning Algorithm (Hypothesis, Loss Functions, Derivatives and Optimization
Algorithms), Gradient Descent, Stochastic Gradient Descent, Linear Regression, Nonlinear Regression,
Perceptron, Support vector machines, Kernel Methods, Logistic Regression, Softmax, Neural networks);
Unsupervised learning: K-means, Density Based Clustering Methods (DBSCAN, etc.), Gaussian mixture
models, EM algorithm, etc.; Reinforcement learning; Tuning model complexity; Bias-Variance Tradeoff; Grid
Search, Random Search; Evaluation Metrics; Reporting predictive performance

Books
Text Book

Machine Learning: A Probabilistic Perspective, 1st Edition, Kevin R Murphy

1. Pattern Recognition & Machine Learning, 1st Edition, Chris Bishop

Probability and Statistics

Credit Hours: 3

Course Description
This course will provide the understanding of the basic concepts in probability, conditional probability
and independent

Course Objectives
To introduce the concepts of data analysis, presentation, counting techniques, probability and decision
making.

Course Outlines
Introduction to Statistics, Descriptive Statistics, Statistics in decision making, Graphical representation of Data
Stem-and Lead plot, Box-Cox plots, measures of central tendencies and dispersion, moments of frequency
distribution; Counting techniques, introduction to probability, sample space, events, laws of probability,
Conditional probability and Baye’s theorem with application to random variable (Discrete and continuous)
Binomial, Poisson, Geometric, Negative Binomial Distributions; Exponential Gamma and Normal distributions.
Regression and Correlation, Estimation and testing of hypotheses, use of elementary statistical packages for
explanatory Data analysis.

Books
Text Book

Ronald Walpole, Myers, Myers, Ye, “Probability & Statistics for Engineers & Scientists”, 8th edition,
2008, Prentice Hall Publisher

Reference Book:

1. Lay L. Devore, Probability and Statistics for Engineering and the Sciences, 2003, Duxbury Publishers.
2. G. Cowan, Statistical Data Analysis, 1998, Clarendon, Oxford.
 Block chain Technology
Course Code:
Credit Hours: 3

Course Description
This course is to provide conceptual understanding of how blockchain technology can be used to
innovate and improve business processes.

Course Objectives
1. Sound familiarity with the Importance and core concepts of Blockchain
2. Architecture, design, mining and consensus algorithm of blockchain especially in bitcoin in depth
Etherium and hyperledger fabric
3. Implement different applications using blockchain technology

Course Outlines
Basic Introduction of the course and the agenda Introduction to useful terminologies, Hash and its usage, Digital
Signature, Authenticity and managing integrity. Need to manage and check integrity, what is Blockchain? How
Bitcoin is related to Blockchain? History of Bitcoin, How Bitcoin Works, Transactions, Blocks, Mining, and the
Blockchain, Bitcoin Transactions, Transactions Inputs and Outputs, Constructing a Transactions, Bitcoin Mining
o Mining Transactions in Blocks, Spending the Transaction, A simple Cryptocurrency, Centralization vs
Decentralization, Distributed Consensus, Consensus without identity using a blockchain, Security of a bitcoin
and attacks, Bitcoin Security, The Root of Trust, User Security Best Practices ▪ Physical Bitcoin Storage,
Hardware wallets, Incentives and proof of work, Mining and proof of work, Mechanics of bitcoin, bitcoin scripts
and its applications, Structure of a Block, Block Header, Block Identifiers: Block Header Hash and Block
Height, The Genesis Block, Linking Blocks in the Blockchain, Merkle Trees and Simplified Payment
Verification (SPV), Payment services with bitcoin, Blockchain Applications, Building Blocks (Primitives),
Applications from Building Blocks, Colored Coins, Colored Coins Transactions Payment Channels and State
Channels, Making Trustless Channels, Routed Payment Channels (lightning Network)

Books
Text Book
The Basics of Bitcoins and Blockchains by Antony Lewis

Reference Book

Blockchain Revolution by Don and Alex Tapscott