Instructor: Dr. Catia S. Silva

Email:catiaspsilva@ece.ufl.edu

Phone: (352) 392-6502

Office Location: NEB 467

Office Hours: Wednesdays 2pm-4pm or by appointment

Slack: uf-ece-fml-fall23.slack.com

Teaching Assistant (TA)/Supervised Teacher (ST)/Undergraduate Peer Instructor (UPI): Name: Raul Valle, UPI

Office Hours: Tuesdays 3pm-5pm (MAE-B 328 or Zoom)

Name: Joshua Lamb, UPI

Office Hours: Mondays 10am-12pm (MAE-B 328 or Zoom)

Name: Joseph Conroy, TA

Office Hours: Thursdays 3pm-5pm (MAE-B 328 or Zoom)

Name: Yu Feng, TA

Office Hours: Wednesdays 9:30am-10:30am, Thursdays 1pm-2pm (Zoom only)

Name: Myles Tan, ST

Office Hours: Tuesdays 1pm-3pm (MAE-B 328 or Zoom)

Course Description

(3 credits) Engineering and hardware concepts pertaining to design of intelligent computer systems.

Course Pre-Requisites / Co-Requisites

None.

Students may not take this course if they have already taken EEE4773.

Course Objectives

Understand and utilize the concepts of machine learning for data science and electrical engineering. Focus on tools for multivariate data analysis and how to handle uncertain data with probability models.

Upon completion of this course, the student will be able to:

.     Identify relevant real-world problems as instances of canonical machine learning problems.

.     Design and implement effective strategies for data preprocessing.

.     Explain and utilize concepts of machine learning for data science and electrical engineering

.     Compare and contrast evaluation metrics

.     Foresee and mitigate human-based liabilities of machine learning algorithms

.     General level of competency in critical questioning and analysis

.    Students will knowhow to make connections between different fields of machine learning

Materials and Supply Fees

None

Required Textbooks and Software

1.    Required Software/Hardware:

.    A computer with the following software installed:

o Python 3.4.3 or later

o Anaconda Distribution o Git

Please see the computer requirements for minimum hardware requirements.

2.     Required Textbooks:

. Pattern Recognition and Machine Learning

o Christopher Bishop

o Springer, 2006

o ISBN: 978-0-38731-073-2

The textbook is freely available as a digital pdf and is perfectly fine for this course.

RecommendedMaterials

. Introduction to Machine Learning

o EthemAlpaydin

o 3rd  edition

o The MIT Press, 2014

o ISBN: 978-8-120-35078-6

This book is freely available online via Course Reserves (you can easily access it under the “Course Reserves” tab in our Canvas page)

. Mathematics for Machine Learning

o Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon

o Cambridge University Press, 2020

o ISBN: 978-1-108-45514-5

The textbook is freely available as a digital pdf and is perfectly fine for this course.

All textbooks are listed and available online through Course Reserves. You can also find this information under the icon “Course Reserves” in our Canvas page.

Course Schedule

The following schedule is tentative and may vary due to time constraints.

Attendance Policy, Class Expectations, and Make-Up Policy

Excused      absences       must      be       consistent      with       university      policies       in      the       Graduate      Catalog (https://catalog.ufl.edu/graduate/regulations) and require appropriate documentation. Additional information can be found here: https://gradcatalog.ufl.edu/graduate/regulations/

Please carefully read the following 8 topics pertaining to class expectations and make-up policies:

1. Course Communications

General information: (a) The primary means to get help with a problem, other than office hours, will be the    Canvas discussion boards. We will check the board daily, to answer inquiries. Other students should feel free to post responses to these questions as well within the guidelines discussed in the sections on collaboration and course etiquette.

(b) Questions about grades or personal issues maybe emailed to meatcatiaspsilva@ece.ufl.eduor within Canvas. You are welcome to use the telephone (352.392.6502), talk with me during office hours, or setup an appointment.

(c) We have a Slack page for the course: uf-ece-fml-fall23.slack.com. This is an optional resource for students to discuss the course amongst each other and with the Professor. This resource is intended to supplement office hours and student interactions. No official communication/submission happens over Slack. No assignments submissions will be accepted over Slack.

Expectations: if you have an issue or need help, do not wait to ask about it! Problems are generally easier to solve sooner rather than later. You are expected to contribute to the ongoing constructive feedback that is an essential   part of the learning process.

2. Attendance Policy

General information: attendance is not required though summative and cumulative assessments, such as practice quizzes, collaborative teamwork, graded exercises, and participation, will happen during synchronous class meetings (including in an online setting, if any).

Expectations: I will prepare course materials with the expectation that students will attend class synchronously and bring a computer to follow along with any practical implementations.

3. Grading Policy

General information: (a) all assignments will have a grading rubric and submissions will be graded based on the assignment’s rubric. For maximum credit, students must submit correct and elaborated answers that follow instructions. For assignments that require code, clean, easy to read, easy to run, and well commented Python code is required.

(b) Individual assignments will not be graded on a curve. Final grades course grades will be graded on a curve.

Expectations: I will expect that students will complete all assignments with care, ensure that submissions are complete and illustrate the understanding of the concepts being assessed.

4. Late Work

General information: all submissions are accepted until the assignment solutions are posted but will lose the “on- time” points listed in the rubric.

Expectations: I will expect students to follow all deadlines. In case of conflict, I expect that students will

communicate with me and let me know well in advance about any conflicting issues in order to avoid losing the “on-time” points.

5. Make-Up Policy

General information: (a) if you feel that any graded assignment needs to be re-graded, you must discuss this with the instructor within one week of grades being posted for that assignment. If approved, the entire assignment will  be subject to complete evaluation.

(b) if you have an academic conflict with any assignment or exam date/time, please let me know well in advance so we can make the necessary changes and make the appropriate accommodations available.

Expectations: I will expect that students will communicate with me and let me know well in advance about any conflicts or time/date change requests.

Excused absences must be consistent with university policies in the undergraduate catalog

(https://catalog.ufl.edu/ugrad/current/regulations/info/attendance.aspx)andrequireappropriate documentation.

6. Collaboration

General information: in solving any individual assignments, healthy discussion and collaboration amongst classmates is encouraged. Healthy collaboration includes: (a) discussing and explaining general course material; (b) discussing assignments for better understanding; (c) aiding for general programming and debugging issues.

Expectations: if another student contributes substantially to your understanding of a problem, you should cite this student to let myself and the teaching assistants be aware of your similar interpretations of a problem. You will not be negatively judged for citing another student.

7. Cheating and Plagiarism

General information: while collaboration is encouraged, you are expected to submit your own work and follow   the student honor code. Submitting work completed by another student is considered plagiarism and will be dealt according to university policy. In general, if you do not understand your solution, the work is not your own.

Examples of plagiarism include: (a) copying (or allowing someone to copy), even partially, an assignment solution or program from the course; (b) submitting material, particularly code, using material taken from another source without proper citation; (c) obtaining solutions to assignments or exams through inappropriate means.

Note that I may elect to use a plagiarism detection service in this course, in which case you will be required to submit your work to such a service as part of your assignment.

Expectations: I expect all students to be bound to the honor pledge as indicated in the student honor code. If you  are suspected of dishonest academic activity, I will invite you to discuss it further in private. Academic dishonesty  will likely result in grade reduction, with severity depending on the nature of the dishonest activity. I am obligated to report on academic misconduct with a letter to the department, college and/or university leadership. Repeat

offences will be treated with significantly greater severity.

8. Course Etiquette

.    Be present. This will allow you to get the most out of class time as well as for your classmates to get the most out of their collaborations with you.

.     Put your cellphone away unless you are actively using it to further the class activities.

.     Be prepared. The readings and videos are carefully chosen to support the in-class activities.

.     Listen carefully and do not interrupt others.

.     Give quality feedback. What constitutes “quality” will be discussed in class.

.     Respect the opinions of others, even when you do not agree.

.     Keep an open mind, embrace the opportunity to learn something new.

.    Avoid monopolizing the discussion. Give others a chance to contribute and be heard.

.     Do not be afraid to revise your ideas as you gather more information.

.    Try to look atissues from more than one perspective.

.     Respect others by learning and using the name and pronoun they prefer.

.     Do not use offensive language.

Evaluation of Grades

Assignment descriptions:

. Homework: will consist of practical and theoretical understanding of the topics covered in class. A typical homework will have two components: Part I – consists of a quiz that will access theoretical understanding; Part II – consists of practical problem/s to be implemented in Python.

. Participation: throughout the course I will ask for participation on a given topic in the form of class

discussion boards. Participation points will be awarded for those posts/discussions and participation in

class. Instructions on participation points will be discussed in the first lecture. The first participation points are awarded in week 1 and 2, so please keep an eye out for these.

. Short Assignments: will consist of exercises for direct application of topics learned in class, it can include code implementation, data analysis or derivations. These assignments have a shorter timeframe for

completion than atypical homework.

. Exams: the exams will be drawn evenly from all lectures, assignments, and readings that occurred up to that point in the course. The exams will have similar questions to those asked in Part I of homework and short assignments. The final exam does not include content from lectures prior to the midterm, although some concepts are in nature cumulative. You are responsible for all assigned material. A full practice

exam(s) will be posted in canvas.

. Final Project: The final project is a group assignment. The objective of this project is to implement an end- to-end Machine Learning/Deep Learning model using a data set collected from students in the class. The

outcomes of the final project include working code, README file and technical report.

Grading Policy