ICS 590 Special Topics In Deep Learning

(Term 212)

Current Catalog Description

The course provides the state of the art and state of the practice in Deep Learning. Advanced topics in loss functions, optimization, back-propagation, feed-forward networks, convolutional neural networks, objects detection, objects segmentation, residual networks, transfer learning, hyper-parameters, neural networks training, recurrent neural networks, long short-term networks, gated recurrent networks, encoder-decoder networks, attention mechanism, transformers, BERT, few-shot techniques, and Generative adversarial network will be discussed.
Note: The course could not be taken for credit with ICS 504

Instructor

Hamzah Luqman

Class meetings

Sunday, Tuesday 17:20 - 18:35 pm; Building 59 room 2002

Office hours

UT: 10:00 am - 10:45 am, 04:00 pm - 04:45 pm and by appointment!

Blackboard

https://blackboard.kfupm.edu.sa/

MS Teams

ICS 590

Instructor Email

hluqman@kfupm.edu.sa

Course Objectives

• Apply advanced concepts of implementation, training and evaluation of deep neural networks
• Learn the state-of-the-art deep learning techniques and architectures
• Improve research skills by emphasizing research techniques and writing papers in topics related to deep learning

Course Learning Outcomes

After completion of this course, the student shall be able to:

• Explore multiple deep learning architectures and understand how to fine-tune and continuously improve models
• Apply advanced techniques of deep learning for developing efficient neural networks
• Implement, train, and evaluate deep neural networks
• Conduct research in deep learning

Prerequisites

ICS 557-Advanced Machine Learning or Consent of Instructor

Textbook

• Deep Learning, Ian Goodfellow, Aaron Courville, and Yoshua Bengio, MIT Press

Useful Resources

• CS231n Convolutional Neural Networks for Visual Recognition, Stanford
• Dive into Deep Learning
• Neural Networks and Deep Learning
• Machine Learning, Oxford
• Deep Learning, New York University
• Deep Learning, CMU
• Deep Learning, University of Maryland
• Hugo Larochelle’s Neural Networks class

Grading

• 10% Quizzes
• 15% Homeworks
• 05% Paper Review
• 25% Term Paper Project
• 15% Midterm
• 30% Final Exam

Late policy for deliverables

• Every student has 4 free late days (one day per homework) for this course.
• After all free late days are used up, penalty is 25% for each additional late day.

Important notes

• Students are expected to be courteous toward the instructor and their classmates throughout the duration of this course.
• All cell phones and e-devices must be “on silent” mode during the classes and “turned off” during the exam times.
• Attendance is taken at the beginning of the class.
• Unexcused Lecture Absences Policies: Two late attendances are considered as one absence. Six unexcused absences result in DN grade.
• An unexcused absence can become an excused absence ONLY by an official letter and must be presented as soon as possible.
• Assignments must be submitted on the due date.
• No make up for exams or any other class work will be made.
• Any issues related to grading should be raised within one week of the release of the grades
• ZERO-TOLERANCE for CHEATING, whether in exams, quizzes, written/programming assignments, and course project. Plagiarism, copying and other anti-intellectual behavior are prohibited by the university regulations.