CSC 594 Topics in Artificial Intelligence

Noriko Tomuro

Office: CDM 648
Winter 2019-2020
Class number: 25443
Section number: 801
Tu 5:45PM - 9:00PM
LEWIS 01105 Loop Campus


This course will be a graduate seminar in advanced deep learning.  It was only a few years ago when deep learning first started to revolutionize Artificial Intelligence (AI) and Machine Learning (ML).  Since then, deep learning has been continuing to advance the state-of-the-art of AI and ML at a super-exponential speed. Deep learning has been successfully applied in a wide range of areas and tasks such as self-driving cars, medical image diagnosis, robotics, machine translation and digital assistants to name a few. 

Deep learning is a type of machine learning algorithms applied on complex neural networks. Since neural network itself is a long-standing topic in AI, its fundamental concepts and principles developed in AI for neural networks are carried over in deep learning such as gradient descent and backpropagation. But in deep learning, new approaches and advanced techniques were invented to exploit the deep complex network architectures. More recently, deep learning has been combined with other ML techniques such as reinforcement learning, multimodal fusion and unsupervised learning.

This course will sample some of the recent and advanced topics in deep learning including:

  • model ensembling
  • transfer learning (and fine-tuning)
  • attention models
  • deep reinforcement learning
  • generative models (e.g. Generative Adversarial Network)

Application data domains will be mostly images and text. Some concepts in Natural Language Processing (NLP) will also be discussed.


There is no required textbook.  Lecture materials and selected research/reference articles will be made available to the students. 


The grade breakdown will be as follows:

   Homeworks      65%
   Final Project  30% 
   Participation   5%


The official, general prerequisite for CSC 594 is "PREREQUISITE(S): For specific prerequisites, see syllabus or consult course instructor."  For this class, the prerequisite is "CSC 578 (Neural Networks and Deep Learning), or consent of the instructor."

This class is intended for graduate students who have taken CSC 578.  Students who have not taken CSC 578 should be familiar with the basic concepts of deep learning and have experience implementing deep learning models.  Students are also expected to be proficient in Python and some common ML packages/tools, while Google TensorFlow/Keras will be used in the class for code demonstration.

School policies:

Changes to Syllabus

This syllabus is subject to change as necessary during the quarter. If a change occurs, it will be thoroughly addressed during class, posted under Announcements in D2L and sent via email.

Online Course Evaluations

Evaluations are a way for students to provide valuable feedback regarding their instructor and the course. Detailed feedback will enable the instructor to continuously tailor teaching methods and course content to meet the learning goals of the course and the academic needs of the students. They are a requirement of the course and are key to continue to provide you with the highest quality of teaching. The evaluations are anonymous; the instructor and administration do not track who entered what responses. A program is used to check if the student completed the evaluations, but the evaluation is completely separate from the student’s identity. Since 100% participation is our goal, students are sent periodic reminders over three weeks. Students do not receive reminders once they complete the evaluation. Students complete the evaluation online in CampusConnect.

Academic Integrity and Plagiarism

This course will be subject to the university's academic integrity policy. More information can be found at If you have any questions be sure to consult with your professor.

Academic Policies

All students are required to manage their class schedules each term in accordance with the deadlines for enrolling and withdrawing as indicated in the University Academic Calendar. Information on enrollment, withdrawal, grading and incompletes can be found at

Students with Disabilities

Students who feel they may need an accommodation based on the impact of a disability should contact the instructor privately to discuss their specific needs. All discussions will remain confidential.
To ensure that you receive the most appropriate accommodation based on your needs, contact the instructor as early as possible in the quarter (preferably within the first week of class), and make sure that you have contacted the Center for Students with Disabilities (CSD) at:
Lewis Center 1420, 25 East Jackson Blvd.
Phone number: (312)362-8002
Fax: (312)362-6544
TTY: (773)325.7296