Dan Ventura
3324 TMCB
(801) 422-9075
Hours: By appointment

Meeting Time & Place

3:00–3:50 MWF
3718 HBLL (Harold B. Lee Library)

The Schedule has dates and deadlines for
lectures, reading, assignments, and exams.

Course Description

This course will introduce a variety of topics in the broad areas of neural networks and machine learning, giving students a solid basis for further research in the field. We will study some fairly well-established techniques that are not covered in CS478 as well as some much more recent work. The goals of the course are to provide a foundation for studying in these growing fields, to attempt to assimilate and synthesize the different models to general principles, and to provide an idea of both the strengths and weaknesses of neural and machine learning approaches to problem solving. Topics will include ensembles, recurrent networks, support vector machines, and manifold learning. As time allows, other topics that may be covered include PAC-learning, learning transfer, spectral methods, reinforcement learning, spiking neurons and other topics of interest.


We will not use a text for the course; instead, we will read papers from the literature. You are responsible for reading the material for a given day prior to that day's discussion. Because class time is limited, we may not cover everything in the reading. However, except where specifically noted otherwise, you are responsible for the entire reading assignment. Most papers will be available online. Any that are not will be provided to you in plenty of time for you to do your reading.

Make sure you have done the reading and tried to understand on your own before you ask questions. If you do not, it is usually readily apparent. This can lead to crankiness, and crankiness never was happiness. When you don't understand something, ask—there are no dumb questions, unless you haven't done your reading.

Attendance & Participation

Class attendance and participation is expected (note that 5% of your grade is based upon it). This is not because I feel the need to have students in class; instead, it is because your attendance and participation guarantee you a better learning experience.

Remember, this is a graduate course—that means more freedom, more fun and more responsibility.


A major part of this course will involve your development of a class project. This will involve significant outside study and preparation on your part and will consist of both a written paper and an oral presentation to the class. Ideally, the paper can evolve into a publishable paper and the oral presentation will give you some experience in presenting your research before peers. We will discuss details and possible topics and approaches early in the semester, and since this a major project that will be due near the end of the semester, you will have to start on it well before we have covered some of the material in class. This facilitates your learning to perform research on your own. An example of an acceptable project is to thoroughly research and present an overview of a topic we do not cover in class. An example of a better project is to attempt some modification, extension or improvement to existing work. The best type of project involves your best efforts at producing some novel results (new algorithm, theoretical results, etc.)

As a preliminary step in this process, everyone will take a turn making a 5-10 minute presentation to the class on the main points of an article from the current literature that deals with a topic of interest. We will have one presentation per day during the middle of the semester. Please check with me in advance to clear your topic.


There will be one mid-term (take-home), which will count for about one third of your final grade, and which will cover material in the reading assignments and class discussions. The in-class presentation of your semester project will count as your final exam, and you will be graded on your presentation content, your organization, your ability to “tell a story” and manage time and your ability to answer questions. This will count about 20% of your project grade.


Grading will be on a weighted curve. An approximate breakdown is as follows:

10% Homework
50% Project (including presentation
5% Attedance & Participation
35% Midterm Exam

Although your final class grade will not be available until the end of the term, a cumulative point total will be available online and will be updated as appropriate. You should check this periodically to ensure that my records are in accordance with the work you have done.

Appealing grades on assignments and on tests begins with you. Make an effort to understand why you received the score that you did and make sure that you have a good reason to appeal. If after making these efforts, you still have a concern, come see me.

Late Policy

Late assignments will be penalized 10% per day late, not counting Sundays. However, if you have a good excuse (i.e. something different from your fellow students) just come and talk to me about it (beforehand, if at all possible), and you will not be penalized. Of course, nothing will be accepted after the last day of class.

Working Together

You may work together with other members of the class; however, do NOT turn in other people's work. This is a fine line that may require some judgment on your part. Examples of acceptable collaboration: discussing homework problems and solutions with others in the class; posting questions and/or answers to the class newsgroup; bouncing project ideas off classmates. Unacceptable collaboration would be simply copying homework answers from a friend; allowing someone else to copy homework answers; plagiarism while writing your project paper. Academic dishonesty will be grounds for failure of the course; however, I do not anticipate that we will have any questions or problems in this area.

Preventing Sexual Harassment

BYU's policy against sexual harassment extends not only to employees of the university, but to students as well. If you encounter sexual harassment, gender-based discrimination, or other inappropriate behavior, please talk to your professor or department chair, or contact the BYU Equal Employment Opportunity Office at 422-5895, or contact the Honor Code Office at 422-2847.

Students With Disabilities

BYU is committed to providing reasonable accommodation to qualified persons with disabilities. If you have any disability that may adversely affect your success in this course, please contact the University Accessibility Center at 422-2767. Services deemed appropriate will be coordinated with the student and instructor by that office.