---

Zoran Kostic, PhD

Associate Professor of Prof. Practice, Electrical Engineering Dept., Columbia University.
zk2172@columbia.edu, webpage, Office hours: Th. 11:30am-1pm, Shapiro 813, (for email communication - use subject: E4040 deep learning from student)

Course Assistants:

Tingyu Mao, Jingyu Qian, Pablo Vicente Juan, Abhishek Jindal, Wenyu Fu, Abhishek Bhatia, (common email e4040TAs@columbia.edu).

---

Course Description

The course covers theoretical underpinnings, architecture and performance, datasets, and applications of neural networks and deep learning. The course will use TensorFlow deep learning framework and Google Cloud computational platform with GPUs. The main resource for the course is the book entitled "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press, http://www.deeplearningbook.org, 2016.

Students will contribute to the course by:

• Working on homeworks: Students can collaborate in groups of 2 or 3, but each student has to write his/her own code and report, and list the names/CUID of collaborators
• Group projects, with no more than 3 students, based on contemporary papers or original ideas. Projects will have to be documented in code, a report, presentation/slides and (possibly) a website.
• Doing one exam/test covering the theory and deep learning architecture and design concepts. The exam will be after the break, closed book
• Collecting the data and providing analysis for a self-contained data-collection project
• Class activity

There will be 4 homeworks. The first, homework 0, will help you ascertain the programming know-how needed to solve the following homeworks. All homeworks will be graded. If you have difficulties with homework 0, please carefully evaluate whether you will have enough time to brush up your programming knowledge by the end of the change of program period. The course requires theoretical background in probability and statistics and linear algebra. You are strongly advised to drop the class if you cannot satisfactorily finish questions of homework #0 by the add/drop date, or if you judge that the first lecture description of prerequsite linear algebra and probability/statistics may be overly demanding.

---

Computational Environment and Prerequisites

---