Course description

Deep learning is a new methodology to train hierarchical machine learning models, such as neural networks. Over the last few months deep learning has produced breakthrough results in many different application areas including speech recognition, image understanding and drug design. The results have been so impressive that even the popular press has taken notice: for example, here is a link to a recent front-page article of the New York Times discussing deep learning in layman's terms.

In this course we will learn about the technical advancements that have enabled these successes by reading and discussing recently published papers in this area. Students will present articles and write paper critiques. In addition, students will be required to propose and complete a term project in the area of deep learning. There is no midterm or final exam.

Administrative information

Instructor

Lorenzo Torresani | 109 Sudikoff | office hour: by appointment

Lectures

Tue&Th 10-11:50am | x-hour (used occasionally to make up cancelled classes) W 3:00-3:50pm
Location: Sudikoff 213

Grading and policies

Grading scheme

The final course grade will be based 20% on in-class participation, 20% on the written critiques, 20% on the paper presentations, and 40% on the term project.

Prerequisites

Computer Science 74/174 (Machine Learning), no exceptions.

Project Schedule

Project proposal (write-up + presentation): 4/21/2015.

Project milestone (write-up + presentation): 5/14/2015.

Project final presentation: 6/2/2015.

Project final write-up: 6/7/2015.

Late submissions

Late submissions will not be accepted under any circumstances: you will get a zero grade for any late submission.

No-laptop policy

We have a no-laptop policy in class (texting, sleeping or engaging in other activities unrelated to the lecture is also forbidden). This policy will be strictly enforced so as to encourage active participation by all students and to avoid distracting people that are focusing on the lecture.

Auditing

Please contact the instructor if you would like to audit the course.

Academic integrity

In order to encourage independent critiquing and to foster in-class discussion, you will NOT be permitted to talk about the assigned papers with your classmates before the lecture: I am interested in hearing your own personal views of the articles and not consensus opinions emerged from group discussions held before the lecture.

You are allowed to use external software for portions of your project. However, you should clearly report the use of external code and include pointers to such software in your project write-up. The project grade will be based on the novelty of your solution/application but also on the amount of new code written by you to implement the idea. So keep this in mind when considering to use software written by someone else.

These rules will be strictly enforced and any violation will be treated seriously