CS490 Advtopics Bese7 - PDF

National University of Sciences & Technology (NUST)
School of Electrical Engineering and Computer Science (SEECS)

Department of Software Engineering
Adv Topics in Computing (Deep Learning)

Course Code: CS-490 Semester: 8th
Credit Hours: 3 Prerequisite Codes: None
Instructor: Omar Arif Class: BESE 7AB
Office: A-110 Telephone: 051-9085-2167
Lecture Days: Tuesday, Friday E-mail: omar.arif@seecs.edu.pk
Class Room: Consulting Hours: Tuesday 3pm-5pm, or by appointment
Lab Engineer: NA Lab Engineer Email: NA
Knowledge Group: Updates on LMS: After every lecture
Course Description:
Deep Networks have revolutionized computer vision, speech recognition and language translation. They have
growing impact in many areas of science and engineering. This course aims to cover the basics of Deep
Learning and some of the underlying theory with a particular focus on supervised Deep Learning, with a good
coverage of unsupervised methods.
Course Learning Outcomes (CLOs):

At the end of the course the students will be able to: PLO BT Level*
1. Identify the deep learning algorithms which are more appropriate for various types of 1 C-2
learning tasks in various domains.
2. Understand design principles and best practices 2 C-2
3. Implement deep learning algorithms and solve real-world problems. 3 C-3
* BT= Bloom’s Taxonomy, C=Cognitive domain, P=Psychomotor domain, A= Affective
domain
Mapping of CLOs to Program Learning Outcomes
PLOs/CLOs CLO1 CLO2 CLO3

PLO 1 (Engineering Knowledge) √
PLO 2 (Problem Analysis) √
Page 1 of 4
PLO 3 (Design/Development of Solutions) √

PLO 4 (Investigation)
PLO 5 (Modern tool usage)
PLO 6 (The Engineer and Society)
PLO 7 (Environment and Sustainability)
PLO 8 (Ethics)
PLO 9 (Individual and Team Work)
PLO 10 (Communication)
PLO 11 (Project Management)
PLO 12 (Lifelong Learning)
Grading Criteria (In accordance with the NUST statutes)
Assessments
 Quizzes: 10%
 Assignments: 10%
 OHT-1: 15%
 OHT-2: 15%
 End Semester Exam: 40%
 Project 10%
Total : 100 %
To be filled in at the end of the course.
Books:
Text Book: 1. Deep Learning by Ian Good Fellow, Y Bengio, G Hinton
Reference 1. Deep learing with Python by F Chollet
Books/Material:
Lecture Breakdown:
Week No. Topics Remarks
1 Deep learning Introduction
2 Artificial Neural Network – Perceptron, loss minimization
3 Artificial Neural Network – Backpropagation, Gradient Descent, Implementation
ANN using PyTorch, Training ANNs
4 Convolutional Neural Network – Visual Recognition, Filtering, Conv and Pooling
Layers, fully connected layer
5 Convolutional Neural Network – Famous CNN architectures
6 OHT-1
7 Object Detection and Segmentation
8 Semantic Segmentation, Instance Segmentation
9 Sequence Modeling, LSTM
10 Natural Language Processing, word embedding
11 Transformer, Attention Models
Page 2 of 4
12 OHT-2
13 Generative Adversarial Networks
14 Autoencoder, Variational Autoencoders
15 Semester Project
16 Semester Project
17
18 ESE
Tools / Software Requirement:

 Python
Grading Policy:
Quiz Policy: The quizzes will be unannounced and normally last for ten minutes. The question framed is to
test the concepts involved in last few lectures. Number of quizzes that will be used for
evaluation is at the instructor’s discretion.
Assignment Policy: In order to develop comprehensive understanding of the subject, assignments will be given.
Late assignments will not be accepted / graded. All assignments will count towards the total
(No ‘best-of’ policy). The students are advised to do the assignment themselves. Copying of
assignments is highly discouraged and violations will be dealt with severely by referring any
occurrences to the disciplinary committee. The questions in the assignment are meant to be
challenging to give students confidence and extensive knowledge about the subject matter
and enable them to prepare for the exams.
Lab Conduct: The labs will be conducted for three hours every week. A lab handout will be given in advance
for study and analysis The lab handouts will also be placed on LMS. The students are to
submit their results by giving a lab report at the end of lab for evaluation. One lab report per
group will be required. However, students will also be evaluated by oral viva during the lab.
Plagiarism: SEECS maintains a zero tolerance policy towards plagiarism. While collaboration in this course
is highly encouraged, you must ensure that you do not claim other people’s work/ ideas as
your own. Plagiarism occurs when the words, ideas, assertions, theories, figures, images,
programming codes of others are presented as your own work. You must cite and
acknowledge all sources of information in your assignments. Failing to comply with the SEECS
plagiarism policy will lead to strict penalties including zero marks in assignments and referral
to the academic coordination office for disciplinary action.
Page 3 of 4
Program Learning Outcomes (PLOs)

Program outcomes are the narrower statements that describe what students are expected to know and be able to
do by the time of graduation. These relate to the knowledge, skills and attitude that the students acquire while
progressing through the program. The program must demonstrate that by the time of graduation the students have
attained a certain set of knowledge, skills and behavioral traits, at least to some acceptable minimum level.
Specifically, it is to be demonstrated that the students have acquired the following graduate attributes:
(i) Engineering Knowledge: An ability to apply knowledge of mathematics, science, engineering

fundamentals and an engineering specialization to the solution of complex engineering problems.
(ii) Problem Analysis: An ability to identify, formulate, research literature, and analyze complex engineering
problems reaching substantiated conclusions using first principles of mathematics, natural sciences and
engineering sciences.
(iii) Design/Development of Solutions: An ability to design solutions for complex engineering problems and
design systems, components or processes that meet specified needs with appropriate consideration for
public health and safety, cultural, societal, and environmental considerations.
(iv) Investigation: An ability to investigate complex engineering problems in a methodical way including
literature survey, design and conduct of experiments, analysis and interpretation of experimental data,
and synthesis of information to derive valid conclusions.
(v) Modern Tool Usage: An ability to 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.
(vi) The Engineer and Society: An ability to apply reasoning informed by contextual knowledge to assess
societal, health, safety, legal and cultural issues and the consequent responsibilities relevant to
professional engineering practice and solution to complex engineering problems.
(vii) Environment and Sustainability: An ability to understand the impact of professional engineering
solutions in societal and environmental contexts and demonstrate knowledge of and need for
sustainable development.
(viii) Ethics: Apply ethical principles and commit to professional ethics and responsibilities and norms of
engineering practice.
(ix) Individual and Team Work: An ability to work effectively, as an individual or in a team, on multifaceted
and /or multidisciplinary settings.
(x) Communication: An ability to communicate effectively, orally as well as in writing, 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.
(xi) Project Management: An ability to demonstrate management skills and apply engineering principles to
one’s own work, as a member and/or leader in a team, to manage projects in a multidisciplinary
environment.
(xii) Lifelong Learning: An ability to recognize importance of, and pursue lifelong learning in the broader
context of innovation and technological developments.
Page 4 of 4

CS490 Advtopics Bese7 - PDF

Uploaded by

Copyright:

Available Formats

CS490 Advtopics Bese7 - PDF

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CS490 Advtopics Bese7 - PDF

Uploaded by

Copyright:

Available Formats

National University of Sciences & Technology (NUST)

School of Electrical Engineering and Computer Science (SEECS)

Adv Topics in Computing (Deep Learning)

Course Learning Outcomes (CLOs):

Mapping of CLOs to Program Learning Outcomes

PLOs/CLOs CLO1 CLO2 CLO3

PLO 3 (Design/Development of Solutions) √

Grading Criteria (In accordance with the NUST statutes)

Tools / Software Requirement:

Program Learning Outcomes (PLOs)

(i) Engineering Knowledge: An ability to apply knowledge of mathematics, science, engineering

You might also like