Course Information

Syllabus

CSCI 479 – Deep Learning
Instructor: Dr. M. Iklé
________________________________________
GENERAL INFORMATION
CSCI 479 will introduce the topic of deep neural networks, along with additional advanced topics in artificial intelligence. The first four weeks will consist of an introduction/review of the basic issues in data mining. During the following two weeks we will introduce basics of deep neural networks using Python and the Python libraries Tensorflow and Keras. During these two weeks, we will be joined by Dr. Hong Liu’s class from Embry-Riddle Aeronautical University in Daytona Beach, Florida. After these two weeks, we will continue learning more advanced techniques in deep learning.

The course will be delivered using a blended learning model that includes multimedia instructional materials, live problem-solving sessions, and team projects.

Course time: Monday, Wednesday, Friday, 10:00 AM – 10:50 AM
Location: POR 234 (Turing Lab)
Office hours,Monday, Wednesday and Friday, 11:00 AM – 12:00 AM

Prerequisite: Approval from instructor.

Required book: François Chollet, Deep Learning with Python, Manning Publications, 2017.

GRADING
Exam 25 %
Team Project 50 %
Participation 25 %

Course Calendar for first four class days
(I will be chairing a conference and will return August 28)

August 20:   Course Introduction, What is Machine Learning?
Powerpoint: Introduction
August 22: Data Preparation
Powerpoint: Data Preparation
August 24: Pre-processing
Youtube video: Pre-processing
Powerpoint: Pre-processing
August 27: Artificial Neural Networks
Youtube video: Neural Networks
Powerpoint: Artificial Neural Networks

Student Learning Outcomes Relevant Program Goal Assessment Measures
Students will learn the main
goals and types of deep
learning.
1, 2, 4 Exam, team projects.
Students will program a
broad variety of real-world
applications of deep
learning.
1, 2, 4 Exam, team projects.
Students will understand
the strengths and
limitations of deep
learning techniques.
1, 2, 4 Exam, team projects.
Students will program
using deep learning
Python libraries.
1, 2, 4 Exam, team projects.
Students will experience
teamwork in handling
real-world deep-learning
projects.
1, 2, 4 Exam, team projects.

CONTENT OUTLINE:
• Fundamentals of machine learning
• Python basics
• Deep Neural Network fundamentals
• Types of layers
• Backpropagation
• Convolutional Neural Networks
• Recurrent Neural Networks
• DNN architectures
• TensorFlow
• TensorFlow-Fold
• TensorFlow-Probability
• Probabilistic Programming

ATTENDANCE POLICY: Your attendance at all lectures and exams is expected. If you miss a class, you are responsible for material that you miss. Attendance will be used to determine borderline grades at the end of the semester.

INCOMPLETES: Incompletes are given only under extraordinary circumstances and only when the student has substantially completed the course work with a passing grade but cannot finish the course for a legitimate reason.

CHEATING: Cheating is defined as submitting work under your name that was not done entirely by you, from memory. Cheating on homework and exams will not be tolerated. Cheating will lead to expulsion from the course with a grade of F.

ADA STATEMENT: Adams State University complies with the Americans with Disabilities Act and Section 504 of the Rehabilitation Act. Adams State University is committed to achieving equal educational opportunities, providing students with documented disabilities access to all university programs, services and activities. In order for this course to be equally accessible to all students, different accommodations or adjustments may need to be implemented. The Office of Accessibility Services (OAS) is located in Richardson Hall 3-100, or available at OAS@adams.edu, and 719-587-7746. They are your primary resource on campus to discuss the qualifying disability, help you develop an accessibility plan, and achieve success in your courses this semester. They may provide you with letters of accommodation, which can be delivered in two ways. You may give them to me in person, or have the Office of Accessibility Services email them. Please make an appointment with their office as early as possible this semester so that we can discuss how potential accommodations can be provided and carried out for this course. If you have already received letters of accommodation for this course from OAS, please provide me with that information privately so that we can review your accommodations together and discuss how best to help you achieve equal access in this course this semester.

STATEMENT REGARDING ACADEMIC FREEDOM AND RESPONSIBILITY: Academic freedom is a cornerstone of the University. Within the scope and content of the course as defined by the instructor, it includes the freedom to discuss relevant matters in the classroom. Along with this freedom comes responsibility. Students are encouraged to develop the capacity for critical judgment and to engage in a sustained and independent search for truth. Students are free to take reasoned exception to the views offered in any course of study and to reserve judgment about matters of opinion, but they are responsible for learning the content of any course of study for which they are enrolled.