Issue Date:11/7/2021 issue:02
ZU/QP10F004
Faculty: Information Technology
Program: Bachelor's degree Department: Data Science
and AI
Semester:
Academic year:
Course Plan
First: Course Information
Credit Hours: 1 Course Name: Deep Learning Lab
Course Number:
1505413
Lecture Time:
Section No.: 1 Prerequisite:-
1505311
Obligatory Faculty Requirement Elective University Requirement ObligatoryUniversity Requirement Faculty Requirement
Course Elective Specialty Requirement Obligatory Specialization requiremen
tType Of Course:
Face-to-Face Learning
Blended Learning(2 Face-to-Face + 1Asynchronous) Online Learning (2 Synchronous+1 Asynchronous) Type of
Learning:
Second: Instructor’s Information
Academic Rank:
Name:
E-mail:
Ext. Number:
Office Number:
Sunday Monday Tuesday Wednesday Thursday Office Hours:
Third: Course Description
Deep learning is a sub-field of machine learning that focuses on learning complex, hierarchical
feature representations from raw data. The dominant method for achieving this, artificial neural
networks, has revolutionized the processing of data (e.g. images, vi deos, text, and audio) as well
as decision-making tasks (e.g. game-playing). Its success has enabled a tremendous amount of
practical commercial applications and has had significant impact on society.
Issue Date:11/7/2021 issue:02
ZU/QP10F004
Fourth: Learning Source
Python Deep Learning Designated Book:
Year: 2019 Print: Second Edition,
Author: Ivan Vasilev
Ian Goodfellow and Yoshua Bengio and Aaron Courville,Deep Learning, An MIT Press book,2016
Jason Brownlee, Develop Deep Learning Models for Natural Language in Python Jason Brownlee, 2017
Additional Sources: Website:
Classroom Laboratory Workshop MS Teams Moodle Teaching Type:
Connection To Program ILOs Code Course Intended Learning Outcomes (CILOs)
Course Code
Knowledge
*PK2, PK3 Concepts and Theories:
Know and understand basic terms associated with deep learning, including motivation, problem formulation, algorithms, and future challenges.
K1**
PK1,PK4 Contemporary Trends, Problems and Research:
Apply the neural network and deep learning techniques to solve modern problems
K2
PK5 Professional Responsibility:
Understand principles, concepts, and neural network architecture of practical problems
K3
Skills
PS2, PS4 Problem solving skills:
Analyze and evaluate the design and implementation of deep learning methods.
S1***
PS1,PS5 Modeling and Design:
Design various deep learning architecture as CNN, RNN, LSTM and BILSTM.
S2
PS4,PS5 Application of Methods and Tools:
Select and apply appropriate methods and computational tools to solve problems using deep learning.
S3
PS3,PS4 General and Transferable Skills - Communication:
Design and construct deep learning systems using appropriate methods.
S4
PS3,PS4 General and Transferable Skills - Teamwork and Leadership:
Be able to communicate effectively in a group S5
Competences
PC4 Critical-Thinking Skills - Analytic skills: Assess
Analyze and evaluate various deep learning architectures as CNN, RNN, LSTM and BILSTM.
C1****
PC4, PC5, Strategic Thinking:
Applying the suitable architecture to the real applications C2
PC1, PC3,PC2,PC6 Creative thinking and innovation:
Solve the problems by using new architecture C3
PC4,PC5 Ethical and Social Responsibility: Understand that they are
accountable for their actions and there must be a balance between economic growth and the welfare of the society and environment.
C4
* P: Program, **K: knowledge, ***S: skills, ****C: competencies.
Fifth: Learning Outcomes
Issue Date:11/7/2021 issue:02
ZU/QP10F004 Lecture
Date
Intended Teaching
Outcomes(ILOs) Topics Teaching
Procedures* Teaching Methods** References***
Week 1 K1, K2, K3, S1 S2
Numpy
Face-to-Face Lecture, In classQuestions Chapter 2 Week 2 K1, K2, K3, S3
Tenserflow
Face-to-Face Lecture, In classQuestions Chapter 3 Week 3 K1, K2, K3, S3 S5
C1, C2, C3
CNN
Applications
Face-to-Face Assignment, PracticalExam, Lab work Chapter 6 Week 4
K1, S1, S2, S3, S4,
S5, C1
Recurrent
Neural Network
Face-to-Face Lecture, In classQuestions Chapter 6 Week 5 K1, K2, K3, S3 S5
C1, C2, C3
RNN
Applications
Face-to-Face Lecture, In classQuestions Chapter 6 Week 6 K1, K2, K3, S3 S5
C1, C2, C3
LSTM
Face-to-Face Lecture, In classQuestions Chapter 6 Week 7
K1, K2, K3, S3 S5
LSTM
Applications
Face-to-Face Lecture, In classQuestions Chapter 6 Week 8
K1, K2, K3, S1 S2
Transfer
Learning
Face-to-Face Lecture, In classQuestions Chapter 6 Week 9 K1, K2, K3, S1 S2
Encoder- Decoder Applications
Face-to-Face Lecture, In class
Questions Chapter 7
Week 10
K1
S2, S3 Transformers
Face-to-Face Lecture, In classQuestions Chapter 7 Week 11
K1, S1, S2, S4, S5,
C1, C4 Transformers
Face-to-Face Lecture, In class QuestionsChapter 7
Week 12 K1, K2, K3, S1 S2
Transformers
Applications
Face-to-Face Lecture, In classQuestions Chapter 7 Week 13 K1, K2, K3, S1 S2
Transformers
Applications
Face-to-Face Lecture, In classQuestions Chapter 7
Week 14
K1, K2, S2, S3, GAN
Applications
Face-to-Face In class Questions Chapter 8* Learning procedures: (Face-to-Face, synchronous, and asynchronous). ** Teaching methods: (Lecture, video…..). ***
Reference: (Pages of the book, recorded lecture, video….).
Seventh: Assessment methods
Methods Fully Electronic Education
Blended Learning
Face-To-Face Learning
Measurable Course (ILOs)
First Exam Second Exam
Mid-term Exam 35 K1, K2, S1, S2, S4, C1,
C2, C3, C2, C5,S2
Participation 15
Asynchronous Activities
Final Exam 50 K1, K2, S1, S2, C4, C5
Sixth: Course Structure
Issue Date:11/7/2021 issue:02
ZU/QP10F004
Eighth: Course Policies
All course policies are applied on all teaching patterns (online, blended, and face-to-face Learning) as follows:
a. Punctuality.
b. Participation and interaction.
c. Attendance and exams.
Academic integrity: (cheating and plagiarism are prohibited).
