Printed on 9/1/2023 6:43:01 PM

LECTURE PLAN

Institute/Department UNIVERSITY INSTITUTE Program Bachelor of Engineering

OF ENGINEERING (UIE) (Computer Science and
Engineering) (Hons.) (with
specialization in Artificial
Intelligence and Machine
Learning) (In association with
IBM) (Lateral Entry)(CS220)
Master Subject Coordinator Madan Lal Saini Master Subject Coordinator E- E13485
Name: Code:
Course Name Deep Learning Course Code 20CSF-432

Lecture Tutorial Practical Self Study Credit Subject Type

3 0 0 0 3.0 T

Course Type Course Category Mode of Assessment Mode of Delivery

Major Elective Graded (GR) Theory Examination (ET) Theory (TH)

Mission of the M1: To provide relevant, rigorous and contemporary curriculum and aligned assessment system to ensure effective learning
Department outcomes for engineering technologies.
M2: To provide platform for industry engagement aimed at providing hands-on training on advanced technological and business
skills to our students.
M3: To provide opportunities for collaborative, interdisciplinary and cutting-edge research aimed at developing solutions to real life
problems
M4: To imbibe quest for innovation, continuous learning and zeal to pursue excellence through hard work and problem-solving
approach
M5: To foster skills of leadership, management, communication, team spirit and strong professional ethics in all academic and
societal endeavours of our students

Vision of the To be recognized as a centre of excellence for Computer Science & Engineering education and research, through effective
Department teaching practices, hands-on training on cutting edge computing technologies and excellence in innovation, for creating globally
aware competent professionals with strong work ethics whom would be proficient in implementing modern technology solutions
and shall have entrepreneurial zeal to solve problems of organizations and society at large.

Program Educational Objectives(PEOs)

PEO1 To be able to explore areas of research, technology application & innovation and make a positive impact in different types of
institutional settings such as corporate entities, government bodies, NGOs, inter-government organizations, & start-ups.
PEO2 To be able to design, and implement technology and computing solutions to the organizational problems, effectively deploy
knowledge of engineering principles, demonstrate critical thinking skills&make the intellectual connections between quantitative
and qualitative tools, theories and context to solve the organizational problems
PEO3 To be able to work with, lead & engage big and small teams comprising diverse people in terms of gender, nationality, region,
language, culture & beliefs. To understand stated and unstated differences of views, beliefs & customs in diverse & inter
disciplinary team settings
PEO4 To be able to continuously learn and update one’s knowledge, engage in lifelong learning habits and acquire latest knowledge to
perform in current work settings
PEO5 To continuously strive for justice, ethics, equality, honesty, and integrity both in personal and professional pursuits. Able to
understand and conduct in a way that is responsible and respectful.

Program Specific OutComes(PSOs)

PSO1 Make valuable contributions in the design, development, and production of computer science and related engineering applications
in the areas of Artificial intelligence and Machine learning.
PSO2 Provide exposure to the latest software tools and technologies related to Artificial intelligence and Machine learning and ability to
practice as an engineer/researcher in the evolving field of AI and ML and its allied application domains by employing project
PSO3 Exhibit proficiency in Artificial Intelligence and Data Analytics for providing solutions to real-world problems in Industry and
Research establishments.

University Information System - By - ERP Division Page 1 of 6

 Printed on 9/1/2023 6:43:01 PM
LECTURE PLAN

Program OutComes(POs)
PO1 Engineering Knowledge: Apply knowledge of mathematics, science, engineering fundamentals and an engineering specialization
to the solution of complex engineering problems.
PO2 Problem Analysis: Identify, formulate, research literature and analyze complex engineering problems reaching substantiated
conclusions using first principles of mathematics, natural sciences and engineering sciences.
PO3 Design/ Development of Solutions: Design solutions for complex engineering problems and design system components or
processes that meet specified needs with appropriate consideration for public health and safety, cultural, societal and
environmental considerations.
PO4 Conduct investigations of complex problems using research-based knowledge and research methods including design of
experiments, analysis and interpretation of data and synthesis of information to provide valid conclusions.
PO5 Modern Tool Usage: Create, select and apply appropriate techniques, resources and modern engineering and IT tools including
prediction and modeling to complex engineering activities with an understanding of the limitations.
PO6 The Engineer and Society: Apply reasoning informed by contextual knowledge to assess societal, health, safety, legal and cultural
issues and the consequent responsibilities relevant to professional engineering practice.
PO7 Environment and Sustainability: Understand the impact of professional engineering solutions in societal and environmental
contexts and demonstrate knowledge of and need for sustainable development
PO8 Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms of engineering practice.

PO9 Individual and Team Work: Function effectively as an individual, and as a member or leader in diverse teams and in multi-
disciplinary settings.
PO10 Communication: Communicate effectively on complex engineering activities with the engineering community and with society at
large, such as being able to comprehend and write effective reports and design documentation, make effective presentations and
give and receive clear instructions.
PO11 Project Management and Finance: Demonstrate knowledge and understanding of engineering and management principles and
apply these to one's own work, as a member and leader in a team, to manage projects and in multidisciplinary environments
PO12 Life-long Learning: Recognize the need for and have the preparation and ability to Engage in independent and life- long learning in
the broadest context of technological Change.

Text Books
Sr No Title of the Book Author Name Volume/Edition Publish Hours Years
1 Neural Networks in Computer Li Min Fu ISE MC GRAW HILL 2007
Intelligence
2 Deep Learning with Python Francois Chollet Second Manning 2021
Publications
3 Deep Learning from Scratch: Seth Weidman First O`Reilley 2019
Building with Python from First
Principles
4 Deep Learning Ian Goodfellow, Yoshua Bengio First MIT Press 2016
and Aaron Courville

Reference Books
Sr No Title of the Book Author Name Volume/Edition Publish Hours Years
1 Fundamentals of Deep Learning Nithin Buduma, Nikhil Buduma Second OREILLY 2022
and Joe Papa Publication
2 Deep Learning: A Practitioners Josh Patterson and Adam First OREILLY 2017
Approach Gibson Publication
3 Deep Learning for Coders with Jeremy Howard and Sylvain First OREILLY 2020
fastai and PyTorch Gugger Publication
4 Deep Learning Using Python S Lovelyn Rose, L Ashok First Wiley Publication 2020
Kumar, D Karthika Renuka

Course OutCome
SrNo OutCome
CO1 Understand the fundamentals of neural network and various deep neural network architectures.

University Information System - By - ERP Division Page 2 of 6

 Printed on 9/1/2023 6:43:01 PM
LECTURE PLAN

CO2 Identify the deep learning algorithms which are more appropriate for various types of learning tasks in
various domains.
CO3 Evaluate the performance of different deep learning models (with respect to the bias-variance trade-off,
overfitting, under fitting, and estimation of test error).
CO4 Design convolution neural networks for object/image classification and improve the performance by
applying optimization techniques.
CO5 Design recurrent neural networks for new data problems based on their requirements and problem
characteristics and analyse their performance.

Lecture Plan Preview-Theory

Mapped with
Pedagogical
Unit No LectureNo ChapterName Topic Text/ Reference Books CO Numer
Tool**
(s)
1 1 Fundamentals Introduction to Neural Network ,T-Neural Networks in Computer PPT CO1
of Neural In,R-Deep Learning: A Practitioners
Network
1 2 Fundamentals Model of Artificial Neuron, Multilayer ,T-Neural Networks in Computer PPT CO1
of Neural Perceptron In,R-Deep Learning: A Practitioners
Network
1 3 Fundamentals Back Propagation ,T-Neural Networks in Computer PPT CO1
of Neural In,R-Deep Learning for Coders with
Network
1 4 Fundamentals Learning rules and various activation ,T-Deep Learning from Scratch: PPT CO1
of Neural functions Bu,R-Fundamentals of Deep
Network Learning
1 5 Fundamentals Gradient descent, Stochastic Gradient ,T-Neural Networks in Computer PPT CO1
of Neural descent. In,R-Deep Learning: A Practitioners
Network
1 6 Neural Network Single layer Feed-forward networks ,T-Neural Networks in Computer PPT CO1
Architecture In,R-Deep Learning Using Python
1 7 Neural Network Multi-layer Feed-forward networks ,T-Deep Learning,R-Fundamentals PPT CO1
Architecture of Deep Learning
1 8 Neural Network Architecture of Back-propagation (BP) ,T-Deep Learning with Python ,R- PPT CO1
Architecture Networks Deep Learning: A Practitioners
1 9 Neural Network Backpropagation Learning ,T-Deep Learning with Python ,R- PPT CO2
Architecture Fundamentals of Deep Learning
1 10 Training Neural Training Deep Neural Networks using ,T-Neural Networks in Computer PPT CO3
Network Back Propagation-Setup and In,R-Deep Learning: A Practitioners
initialization issues,
1 11 Training Neural Gradient- Descent Strategies ,T-Neural Networks in Computer PPT CO3
Network In,R-Fundamentals of Deep
Learning
1 12 Training Neural vanishing and exploding Gradient ,T-Deep Learning,R-Deep Learning PPT CO3
Network problems Using Python
1 13 Training Neural Regularizations and dropouts-1 ,T-Neural Networks in Computer PPT CO3
Network In,R-Fundamentals of Deep
Learning
1 14 Training Neural Regularizations and dropout-2 ,T-Deep Learning with Python ,R- PPT CO3
Network Deep Learning: A Practitioners
1 15 Training Neural Problem discussion/Class test/surprise ,T-Deep Learning with Python ,R- Activity CO1
Network test on unit-1 Deep Learning: A Practitioners
2 16 Convolutional Introduction to Convnet, Convolution ,T-Deep Learning from Scratch: PPT CO1
Neural Network operation Bu,R-Deep Learning for Coders with
2 17 Convolutional Basic structure of Convolutional ,T-Deep Learning with Python ,R- PPT CO1
Neural Network Network Deep Learning: A Practitioners
2 18 Convolutional Filters, Convolutional Layer, Pooling ,T-Neural Networks in Computer PPT CO1
Neural Network Layer, FC Layer In,R-Fundamentals of Deep
Learning

University Information System - By - ERP Division Page 3 of 6

 Printed on 9/1/2023 6:43:01 PM
LECTURE PLAN

2 19 Convolutional Padding and Stride ,T-Deep Learning from Scratch: PPT CO1
Neural Network Bu,R-Deep Learning for Coders with
2 20 Convolutional Data Augmentation ,T-Deep Learning with Python ,R- PPT CO3
Neural Network Deep Learning: A Practitioners
2 21 Convolutional Feature Extraction, Feature map, Fine ,T-Deep Learning from Scratch: PPT CO3
Neural Network Tuning Bu,R-Deep Learning for Coders with
2 22 Case Study on Image classification using Keras ,T-Deep Learning with Python ,R- Simulation CO4
CNN Deep Learning: A Practitioners
2 23 Case Study on Image classification using Pytorch ,T-Deep Learning from Scratch: Simulation CO2
CNN Bu,R-Deep Learning for Coders with
2 24 Case Study on Image classification using Tensorflow ,T-Deep Learning from Scratch: Simulation CO2
CNN Bu,R-Deep Learning: A Practitioners
2 25 Case Study on FCNN Case study Summary ,T-Deep Learning from Scratch: Case Study CO3
CNN Bu,R-Deep Learning: A Practitioners
2 26 CNN Model Introduction to Pretrained Models: ,T-Deep Learning,R-Deep Learning Flipped CO2
Architectures Imagenet, LeNet Using Python Classes
2 27 CNN Model AlexNet, VGGNet ,T-Deep Learning from Scratch: Flipped CO2
Architectures Bu,R-Deep Learning for Coders with Classes
2 28 CNN Model ResNet variations ,T-Neural Networks in Computer Flipped CO4
Architectures In,R-Fundamentals of Deep Classes
Learning
2 29 CNN Model Attention Model: Self Attention, Spatial ,T-Neural Networks in Computer PPT CO4
Architectures Attention, and Residual Attention. In,R-Fundamentals of Deep
Learning
2 30 CNN Model Problem discussion/Class test/surprise ,T-Deep Learning,R-Deep Learning Activity CO2
Architectures test on unit-2 Using Python
3 31 Advance Deep Understanding a Recurrent Neural ,T-Deep Learning with Python ,R- PPT CO1
Learning Networks-1 Deep Learning: A Practitioners
Models
3 32 Advance Deep Understanding a Recurrent Neural ,T-Neural Networks in Computer PPT CO1
Learning Networks-2 In,R-Fundamentals of Deep
Models Learning
3 33 Advance Deep Long Short-Term Memory ,T-Neural Networks in Computer PPT CO1
Learning In,R-Fundamentals of Deep
Models Learning
3 34 Advance Deep Back Propagation Through Time ,T-Deep Learning with Python ,R- PPT CO3
Learning (BPTT) Deep Learning: A Practitioners
Models
3 35 Advance Deep Bidirectional LSTMs ,T-Deep Learning from Scratch: PPT CO2
Learning Bu,R-Deep Learning for Coders with
Models
3 36 Advance Deep Auto Encoder Basics ,T-Deep Learning from Scratch: PPT CO1
Learning Bu,R-Deep Learning for Coders with
Models
3 37 Advance Deep VAE and GAN. ,T-Deep Learning from Scratch: PPT CO5
Learning Bu,R-Deep Learning for Coders with
Models
3 38 Best Practices Monitoring Deep learning model using ,T-Deep Learning with Python ,R- PPT CO1
in Deep Keras Callback and Tensorboard-1 Deep Learning: A Practitioners
Learning
3 39 Best Practices Monitoring Deep learning model using ,T-Deep Learning,R-Deep Learning Simulation CO2
in Deep Keras Callback and Tensorboard-2 Using Python
Learning
3 40 Best Practices Monitoring Deep learning model using ,T-Deep Learning from Scratch: Simulation CO3
in Deep Keras Callback and Tensorboard-3 Bu,R-Deep Learning for Coders with
Learning
3 41 Best Practices Multi-task Deep Learning-1 ,T-Deep Learning from Scratch: PPT CO4
in Deep Bu,R-Deep Learning for Coders with
Learning
3 42 Best Practices Multi-task Deep Learning-2 ,T-Deep Learning with Python ,R- PPT CO5
in Deep Deep Learning: A Practitioners
Learning

University Information System - By - ERP Division Page 4 of 6

 Printed on 9/1/2023 6:43:01 PM
LECTURE PLAN

3 43 Best Practices Multi-view Deep Learning-1 ,T-Deep Learning with Python ,R- PPT CO5
in Deep Deep Learning: A Practitioners
Learning
3 44 Best Practices Multi-view Deep Learning-2 ,T-Deep Learning from Scratch: PPT CO5
in Deep Bu,R-Deep Learning for Coders with
Learning
3 45 Best Practices Problem discussion/Class test/surprise ,T-Deep Learning from Scratch: Activity CO3
in Deep test on unit-3 Bu,R-Deep Learning for Coders with
Learning

Assessment Model
Sr No Assessment Name Exam Name Max Marks
1 20EU01 External Theory 60
2 20EU01 Assignment 10
3 20EU01 Attendance Marks 2
4 20EU01 Mid-Semester Test-1 20
5 20EU01 Quiz 4
6 20EU01 Surprise Test 12
7 20EU01 Mid-Semester Test-2 20

CO vs PO/PSO PSO3 PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2

CO1 3 3 1 2 2 1 NA NA NA 2 1 1 1 3 3

CO2 3 2 2 2 2 2 NA NA NA 2 1 1 1 3 3

CO3 3 2 3 3 3 2 NA NA NA 2 1 2 2 3 2

CO4 3 2 3 3 3 2 NA NA NA 3 1 3 2 3 2

CO5 3 2 3 3 3 2 NA NA NA 3 1 3 2 3 2

Target 3 2.2 2.4 2.6 2.6 1.8 NA NA NA 2.4 1 2 1.6 3 2.4

University Information System - By - ERP Division Page 5 of 6

 Printed on 9/1/2023 6:43:01 PM
LECTURE PLAN

University Information System - By - ERP Division Page 6 of 6