COMS E6998: SW Engineering for AI Systems, Spring 2021

Description 

AI models are increasingly being used in safety-critical systems like autonomous vehicles. This comes with concerns about the quality and reliability of these systems, as several erroneous and sometimes even fatal behaviors have already been reported. However, due to the fundamental architectural differences between AI and traditional software, existing software engineering techniques do not apply to them in an obvious way. In fact, companies like Google, Tesla, etc. are increasingly facing all the traditional software engineering challenges. In this class, we will discuss different Software Engineering practices and challenges model developers are facing for AI-based systems. In particular, we will focus on the quality assurance of the DNN models.

Lecture Details

          Instructor: Baishakhi Ray 
Class Schedule: Monday and Wednesday 1:10 PM - 2:25 PM
           Location: Online (Zoom Link will be posted)
     Office Hours:  Wednesday 2:30 pm - 3:30 pm /appointment 

                 Q&A Forum:

                           Trivia: 

 Office Hours Location: Online (Zoom Link will be posted)

Requirements

     Working knowledge of Deep Neural Network.

   ​

Grading

  • Class Participation: 40%     

  • Project: 60%

 

Team Assignments

Tentative Schedule

Additional Reading:

Policies:

  • Late submissions: No late assignments will be accepted.

  • Academic rules of conduct: Students are expected to adhere to the Academic Honesty policy of the Computer Science Department, this policy can be found in full here.

  • Violations: Violation of any portion of these policies will result in a penalty to be assessed at the instructor's discretion. This may include receiving a zero grade for the assignment in question and a failing grade for the whole course, even for the first infraction.

  • In order to receive disability-related academic accommodations for this course, students must first be registered with their school Disability Services (DS) office. Detailed information is available online for both the Columbia and Barnard registration processes. Refer to the appropriate website for information regarding deadlines, disability documentation requirements, and drop-in hours (Columbia)/intake session (Barnard). Students registered with the Columbia DS office can refer to the Master TARF section of the DS Testing Accommodations page for more information regarding disability-related academic accommodations for this course.

Columbia University

New York City, NY 10027, USA