Adani University, Ahmedabad

Faculty of Engineering Sciences and Technology (FEST)

Department of Computer Science and Engineering (AI-ML)

Course Code :
Course Name : Deep Learning: Principles and Practices
Pre-requisites, if any: Foundation of AI, Machine Learning Essentials
Credit Points :4
Offered : B.Tech in CSE
Semester :6

Course Coordinator:
Full Name: Dr. Tejas M. Modi
Faculty and Address with room number: Department of CSE
Faculty Room: CSE Faculty Room, 4th floor.
Telephone: 07984014074
Email: [email protected]
Consultation Times: 10:00-5:00 Monday to Friday
Students will be contacted throughout the Session via email with important information relating
to this Course.

Course Objectives:

The course objective is to introduce the idea of artificial neural networks and deep learning
models to enable design and deployment of their architectures in real life problem solving.

Course Outcomes:

After learning the course, the students should be able to:

CO-1 Ability to explain the essential concepts of deep learning and to understand the
mathematics behind functioning of artificial neural networks.
CO-2 Ability to understand Feed- Forward Neural Network and Deep Network concepts,
architectures.
CO-3 Ability to explore the Convolution Neural Network and Recurrent Neural Network
concepts, architectures, applications, and case studies.
CO-4 Ability to compare different autoencoders and reinforcement learning techniques, use
cases, and applications.

<Course Code, Course Name, Semester, Year> Page 1 of 10

Course Outline:

Unit Content Hrs.

1 Introduction: Brief introduction to Deep learning basics, Applications: 07
Discuss in detail, Challenges, Neural Network concepts.
Artificial Neural Networks: Neurons, Expressing Linear Perceptron as
Neurons, Linear Neurons and Their Limitations, Activation Functions--
Sigmoid, Tanh, ReLU, Softmax, Output Layers.
2 Feed-Forward Neural Networks: Gradient Descent, Delta Rule and Learning 10
Rates, Gradient Descent with Sigmoidal Neurons, Backpropagation
Algorithm, Stochastic and Minibatch Gradient Descent, Test Sets, Validation
Sets, Overfitting, Preventing Overfitting in Deep Neural Networks, Deep
Belief Network.
Deep Networks: Local Minima in the Error Surfaces of Deep Networks,
Model Identifiability, Spurious Local Minima in Deep Networks, Flat Regions
in the Error Surface, Momentum-Based Optimization, Learning Rate
Adaptation, Vanishing Gradients, Recurrent Neural Network.
3 Convolution Neural Network: Architecture, Accelerating Training with 16
Batch Normalization, different Convolutional Neural Networks, Embedding
and Representation Learning, Convolution Operation, Filters, Pooling
Operation –Max pooling, Average pooling, Global pooling. Dilated CNN,
Evaluation metrics, Applications, Case studies.
Recurrent Neural Networks: Architecture, Attention Mechanism, Vanilla
RNN, LSTM, Bidirectional RNN, Gated Recurrent Unit, Graph Recurrent
Neural Network, Deep RNN, Hierarchical RNN, Applications, Case studies.
4 Autoencoder: Architecture, Types of autoencoder- Sparse AE, Convolutional 12
AE, Variational AE, Applications, Case studies.
Reinforcement Learning: Architecture, Framework---State, Reward, Policy,
Agent, Environment, Action, Types of Learning---Q-Learning, DQN, Policy
Gradient, DDPG, Evaluation metrics, Applications, Case studies.

Method of delivery:
Face-to-face lectures, self-study material, class practice, assignments, quizzes, presentations,
etc.

Study time:
3 hrs. lecture, 2 hrs. lab

CO-PO Mapping (Course outcome with Program Outcomes):

<Course Code, Course Name, Semester, Year> Page 2 of 10

 PO 1. Engineering knowledge: Apply the knowledge of mathematics, science, engineering
fundamentals, and an engineering specialization to the solution of complex engineering
problems.
PO 2. Problem analysis: Identify, formulate, review research literature, and analyze complex
engineering problems reaching substantiated conclusions using first principles of
mathematics, natural sciences, and engineering sciences.
PO 3. Design/development of solutions: Design solutions for complex engineering problems
and design system components or processes that meet the specified needs with
appropriate consideration for the public health and safety, and the cultural, societal, and
environmental considerations.
PO 4. Conduct investigations of complex problems: Use research-based knowledge and
research methods including design of experiments, analysis and interpretation of data,
and synthesis of the information to provide valid conclusions.
PO 5. 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.
PO 6. The engineer and society: Apply reasoning informed by the contextual knowledge to
assess societal, health, safety, legal and cultural issues and the consequent
responsibilities relevant to the professional engineering practice.
PO 7. Environment and sustainability: Understand the impact of the professional engineering
solutions in societal and environmental contexts, and demonstrate the knowledge of,
and need for sustainable development.
PO 8. Ethics: Apply ethical principles and commit to professional ethics and responsibilities
and norms of the engineering practice.
PO 9. Individual and teamwork: Function effectively as an individual, and as a member or
leader in diverse teams, and in multidisciplinary settings.
PO 10. 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.
PO 11. Project management and finance: Demonstrate knowledge and understanding of the
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.
PO 12. 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.

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

CO-1 3 2 2 2 2 0 1 0 0 0 0 2
CO-2 3 3 3 2 3 0 1 0 0 0 2 3

<Course Code, Course Name, Semester, Year> Page 3 of 10

CO-3 3 3 3 3 3 0 1 0 0 0 2 3
CO-4 3 3 3 3 3 0 1 0 0 0 2 3

Blooms Taxonomy and Knowledge Retention:

(Blooms taxonomy has been given for reference)

Figure 1: Blooms Taxonomy Figure 2: Knowledge retention

Remember Understand Application Analysis Evaluate Create

15 25 20 15 15 10

Graduate Qualities and Capabilities Covered

(Qualities graduates harness crediting this Course)

General Graduate Qualities/ Attributes Specific Faculty of Graduate

Capabilities
Deep discipline knowledge & intellectual breadth: • Professional knowledge,
i. Graduates are able to apply domain knowledge from a grounding & awareness
strong understanding of the fundamentals and connect with
the larger picture in the real world.
Creative, critical thinking, and problem-solving: • Complex problems solving
i. Graduates shall not be stuck in the silos of discipline. ability
ii. Graduates shall be able to analyse a problem critically using
• Intellectual and creative
their scientific temper. advances
iii. Graduates shall be solution-centric solving problems
innovatively.
Digital mindset: • Information literacy, literature
i. Graduates shall be able to use technology to enable and gathering & processing, and
enhance their effectiveness and efficiency in delivering use of IT tools
outcomes.
Teamwork and Communication Skills: • Team and individual work

<Course Code, Course Name, Semester, Year> Page 4 of 10

 i. Graduates shall be inclusive in a team acknowledging and • Written and Oral
appreciating the strengths of team members. communications
ii. Graduates shall be able to communicate effectively to
enhance collaboration and comradery.
Professional and leadership readiness: • Leadership role
i. Graduates shall be courteous, and conscientious and exhibit
mastery over their domain of expertise.
ii. Graduates shall exhibit leadership traits of inclusivity,
empathy, understanding, and listening skills encouraging
team spirit.
Human values: • Professional Ethics and human
i. Graduates shall have the five fundamental values of truth, values
right conduct, peace, love, and non-violence as their core • Intellectual integrity
values whereby they do not adhere to practices that are
immoral, unethical, and the like, thereby exhibiting global
citizenship.
ii. Graduates shall exhibit compassion, unity, and inclusivity
in all their engagements.
Self-awareness and emotional intelligence: • Examine the outcome of one’s
i. Graduates shall be aware of their personality and action, Learn from self-
conditionings for appropriate engagement with others. experience
ii. Graduates shall be resilient without being distracted and
detracted by anxiety, fear, superiority, or inferiority complex
and other emotional entropy thereby possessing the ability
to handle any situation with mental equipoise
Sustainability mindset: • Sustainability, societal &
Graduates shall be sensitive to the people and planet in their environmental impacts
every approach.

Practical work:
• Installation and working on various tools viz. Python, ANACONDA, TensorFlow, Keras,
Google Collab, etc. (2 Hours)
• Understanding key technology foundations required application setup for different domain
with Deep Learning. Developing Neural Networks for Regression analysis. (2 Hours)
• Comparative evaluation of deep learning models, i.e., ANN, Feed Forward Neural Network,
CNN, RNN, GNN, Autoencoders, Reinforcement Learning. (Total 10 Hours-----Each Model
Implementation 2 Hours)

Lecture/tutorial times: (Give lecture times in the format below)

Lecture <Day> <Time>

<Course Code, Course Name, Semester, Year> Page 5 of 10

All lectures, tutorials, seminars, and practical work as stipulated in the Course outline. Attendance
of practical work exercises is compulsory and fulfills the attendance criteria as laid down in the AU
regulations (90%).

Details of Referencing System to be used in Written Work:

American Psychological Association (APA)

Attendance Requirements:
The Code of Practice students states that it is the responsibility of students to attend all lectures,
tutorials, seminars, and practical work as stipulated in the Course outline. Attendance of practical
work exercises is compulsory and fulfill the attendance criteria as laid down in the AU regulations.

Textbooks:

1. Simon Haykin, Neural Network by, Pearson Education/PHIX.

2. Goodfellow, I., Bengio, Y., Courville, A., Deep Learning, Part II, MIT Press, 2016.
3. AurélienGéron, “Hands-On Machine Learning with Scikit- Learn and TensorFlow”, O’Reilly,
2017.
4. Nikhil Ketkar, “Deep Learning with Python: A Hands-on Introduction”, Apress, 2017

Reference Books:
1. Josh Patterson, Adam Gibson, Deep Learning: A Practitioner's Approach, O’Reilly, 2017.

Additional Materials:
NPTEL (https://onlinecourses.nptel.ac.in/noc20_cs62/preview )
Stanford University (https://cs230.stanford.edu/syllabus/)
Coursera (https://www.coursera.org/specializations/deep-learning )

Assessment Guidelines:
Your final course mark will be calculated from the following:

Theory Marks (100)

End Semester Examination : 50 Marks
Continuous Evaluation : 50 marks

Practical Marks (50)

Practical Assessment : 25 Marks
Viva : 25 Marks

Supplementary Assessment: (Courses with Academic Empowerment ONLY)

<Course Code, Course Name, Semester, Year> Page 6 of 10

Students who receive an overall mark below the passing benchmark as set-by instructor/ faculty
will be considered for supplementary assessment in the semester concerned. The offer of
supplementary assessment is not automatic and will be considered on a case-by-case basis. A
precise form of supplementary assessment will be determined at the time the offer of a
supplementary assessment is made. Students must make themselves available during the
supplementary examination period to take up any offer of supplementary assessment as
announced by the faculty.

Practical Work Report/Laboratory Journal:

A report on the practical work is due the subsequent week for evaluation by faculty after the
completion of the class by each group.

Late Work:
Late assignments will not be accepted without supporting documentation. Late submission of the
reports will result in a deduction of 5% of the maximum mark per calendar day.

Format:
All assignments must be presented in a neat, legible format with all information sources correctly
referenced. Assignment material handed in throughout the year that is not neat and legible
will not be marked and will be returned to the student.

Retention of Written Work:

Written assessment work will be retained by the Course coordinator/instruction/ faculty for two
weeks after marking to be collected by the students.

Adani University and Faculty Policies:

Students should make themselves aware of Adani University and/or FEST Policies regarding
plagiarism, special consideration, supplementary examinations, and other educational issues and
student matters.

Plagiarism: Students should refer to the policy on Plagiarism available in the Calendar. Plagiarism
is not acceptable and may result in the imposition of severe penalties. Plagiarism is the use of
another person’s work, or idea as if it is his or her own - if you have any doubts at all about what
constitutes plagiarism, please consult your Course coordinator or lecturer. Plagiarism will be
penalized severely which has led to expulsion. Further information on plagiarism can be found in
the Faculty Policy document.

Do not copy the work of other students.

Do not share your work with other students (except where required for a group activity or
assessment

<Course Code, Course Name, Semester, Year> Page 7 of 10

Course schedule: (Mention quiz, assignment submission, breaks, etc as well in the table under
the Teaching Learning Activity Column)

Teaching
Week # Topic & contents CO Addressed Learning
Activity (TLA)

Weeks 1

Weeks 2

Week 3

Week 4

Week 5

Week 6

Week 7

Week 8

Week 9

Week 10

Week 11

Week 12

Week 13

Week 14

<Course Code, Course Name, Semester, Year> Page 8 of 10

 Week 15

<Course Code, Course Name, Semester, Year> Page 9 of 10

 Teaching
Week # Topic & contents CO Addressed Learning
Activity (TLA)

Weeks 1

Weeks 2

Week 3

Week 4

Week 5

Week 6

Week 7

Week 8

Week 9

Week 10

Week 11

Week 12

Week 13

Week 14

Week 15

<Course Code, Course Name, Semester, Year> Page 10 of 10