|
CS165B: Machine Learning: Syllabus |
Syllabus contents:
- General Information
- Prerequisites
- Course Objectives
- Class Attendance
- Textbook
- Computing Facilities
- Assignments and Grading
- Academic Integrity
- Students With Disabilities
Course
web site
Please check the course web site regularly for assigned
reading and homework, announcements, and any other relevant
information.
The
formal prerequisite is Computer Science 130A (Data Structures and Algorithms
I). This implies that you have studied topics such as algorithms, data
structures, searching and sorting techniques, recursion, and induction, all of
which are relevant to this course. Most importantly, you need to be able
to think logically about problems and solution strategies, and you must be
familiar enough with writing software to implement solutions on your own. If
you have completed the CS pre-major courses (including the Math and PSTAT
courses) and CS 130A then you will be well-prepared.
What is this course about?
An introduction to the field of Machine Learning (ML), which attempts to understand and build
machine learning algorithms. Topics include
classification, clustering, representation, ensemble methods, neural
networks and deep learning.
Overview
Machine learning
(ML) is the scientific study of algorithms and statistical models that computer
systems use to perform a specific task without using explicit instructions,
relying on patterns and inference instead. It is seen as a subset of artificial
intelligence. Machine learning algorithms build a mathematical model based on
sample data, known as "training data," in order to make predictions or decisions
without being explicitly programmed to perform the task. Machine learning
algorithms are used in a wide variety of applications, such as email filtering
and computer vision, where it is difficult or infeasible to develop a
conventional algorithm for effectively performing the task (Wikipedia). We will cover the following topics:
Machine Learning Basic Concept
Classification
Clustering
Ensemble Methods
Neural Networks, Deep Learning
What you will learn
By
the end of the course, you will understand what ML is all about and what it has
contributed, and may contribute, to computing. You will have a working
knowledge of the basic tools of machine learning, which are applicable to a wide range of computing
problems. You will be able to solve problems using classification and clustering. You will have experience building
models that, to some degree, can
learn from experience.
This
is not primarily a programming course - that is, the main goal is to learn the
concepts, not to learn a language or particular programming techniques.
However, coding examples of the concepts is the best way to demonstrate (and facilitate)
your knowledge of them. Good programming practices (proper file structure,
comments, etc.) are expected.
You are responsible for everything that goes on in
class. Prepare in advance for class by reading and studying the assigned text,
and by making sure you understand the previous lectures.
Weekly
50-minute discussion sections, led by the TA, will focus on (1)
presenting supplementary material (such as practical examples) to the lectures, (2) answering questions (about lecture topics, homework problems,
programming issues, etc.), or by the instructor for make-up classes. It is required that students attend these sessions;
you are responsible for the material presented in these sessions. Students are
encouraged to give the TAs (and, if appropriate, the instructor) feedback
regarding topics or issues they would like to have discussed during this time.
Machine
Learning: The Art and Science of Algorithms that Make Sense of Data, 1st Edition
by Peter Flach
You
may use the CSIL (Computer Science Instructional Lab) computers, or any other
machine you prefer.
Grades will be based on homework assignments,
machine problems, midterm exam, and final exam:
20% Homework assignments
40% Coding
assignment
20% Midterm exam
20% Final exam
Homework will include 4 assignments and 3 coding assignments.
Unless
otherwise instructed, all assignments must be handed in the class on the due
date.
After the due date, your score will be reduced 20% each day.
You
are encouraged to discuss homework assignments with classmates at a general
level. However, you shall not share answers/code or collaborate on
solutions unless otherwise directed to do so. All work turned in must be
completely your own, including programming assignments. (See the Policy on
Academic Integrity, below.)
There
will be no makeup exams.
Please read this section carefully.
The
university, the department, and this instructor all take the issue of academic
integrity very seriously. A university requires an atmosphere of mutual
trust and respect. While collaboration is an integral part of many scholarly
activities, it is not always appropriate in a course, and it is never
appropriate unless due credit is given to all participants in the
collaboration. This goes for both ideas and programming or other work.
Here are some examples:
Allowed: Discussion of lecture and
textbook materials
Allowed: Discussion of how to approach
assignments, what techniques to consider, what textbook or lecture material is
relevant
Not allowed: Sharing ideas in the form
of code, pseudocode, or solutions
Not allowed: Turning in someone else's
work as your own, even with that person's permission.
Not allowed: Allowing someone else to
turn in your work as his or her own.
Not allowed: Turning in work without
proper acknowledgment of the sources of the content (including ideas) contained
within the work.
Summary:
Academic integrity is absolutely required - dishonesty (cheating, plagiarism,
etc.) benefits no one and hurts everyone. If you are not sure whether or
not something is appropriate, please ask the instructor or TA.
If
you are a student with a disability and would like to discuss special academic
accommodations, please contact the instructor. In addition, students with
temporary or permanent disabilities are referred to the Disabled Students Program (DSP) at
UCSB. DSP will arrange for special services when appropriate (e.g.,
facilitation of access, note takers, readers, sign
language interpreters). Please note that it is the student's
responsibility to communicate his or her special needs to the instructor, along
with a letter of verification from DSP.
Back to home