Course Overview

Course Description

Content
This course introduces topics in Deep Learning with an emphasis on individual inquiry, problem-based learning, group work, and computer programming.

Prerequisites
CS 3460 and MAT 2240 with a grade of "C" or higher

Objectives

1. Build, train, and evaluate models for a variety of deep learning problems;
2. Explore a variety of models that perform well;
3. Demonstrate self-guided learning;
4. Communicate your findings; and
5. Work well with your team.

Course Requirements

Materials

Required

• Jon Krohn, Deep Learning Illustrated
• Can-do attitude!

Resources

• Codecademy
• Udacity
• Khan Academy

Assignments

Attendance

Unexcused absences deduct 1% from your final grade.

Observations of Group Meetings

You will receive a grade based on my observations of your team meetings during class. Attendance is mandatory and although excused absences will not directly affect your grade, neglecting your team will.

Inquiry Reports

Students will submit an inquiry report each week that demonstrates their individual contributions to the team. These should answer what you learned on your own outside of class and group meetings.

Model Performance and Exploration

A significant portion of this class will be spent designing, building, training, and evaluating deep learning models. A portion of your grade will be determined by the timeliness, performance, and diversity of the models you submit to Web-CAT.

Project Reports

Each problem culminates with a group project report. Two students will lead each team's report. Every student must lead at least one problem report. The grade for reports you lead are weighted more in computing your semester report grade: 50% of your grade will be determined by the reports you lead and 50% from your team's average.

Project Presentations

Each problem culminates with a group project presentation. Two students will lead each team's presentation. Every student must lead at least one problem presention. The grade for presentations you lead are weighted more in computing your semester presentation grade: 50% of your grade will be determined by the presentations you lead and 50% from your team's average.

Peer and self evaluations

At the end of each project, will submit self and peer evaluations.

Final Exam

A written exam will be given during the final exam period.

Grading & Policies

Course Policies

University Policies

ASU has official policies that are considered part of this syllabus, including the Academic Integrity Code, accommodations for students with disabilities, Attendance Policy, and the Statement on Student Engagement with Courses:
Syllabi Policy and Statement Information

Additional Syllabus Statements

In addition, this syllabus incorporates the following statements on Food Insecurity, Title IX Reporting Obligations, and Public Sharing of Course Materials:
Optional Syllabi Policy and Statement Information

Grading

• The final grade will determined using the following percentages:

• Category	Percent
  Observations of group work	20%
  Inquiry Reports	20%
  Oral presentations and Technical Reports	15%
  End-of-term self and peer evaluation	15%
  Final Exam	15%
  Performance and Exploration of Models	15%
  Total	100%

• All grades will be posted to ASULearn.
• The maximum percentage required to earn each letter grade is shown below:

• Grade	Percentage Required
  A	93
  A-	90
  B+	87
  B	83
  B-	80
  C+	77
  C	73
  C-	70
  D+	67
  D	63
  D-	60
  F	below 60

  NOTE: Students in CS 5440 with a grade below 70 will recieve an F.

Calendar