Course Information for CS344
Learning Goals
Deep learning is a relatively new and rapidly evolving discipline
that is revolutionizing how computers learn from data.
Students who complete this course will be able to:
- Analyze the fundamental capabilities and limitations of how computers learn.
- Design and implement artificial neural networks.
- Explain the theoretical foundations of deep learning.
- Apply deep learning algorithms to large data sets in a variety of real-world contexts.
- Communicate technical content related to deep learning.
- Identify societal impacts and ethical considerations of deep learning systems.
- Extend existing deep learning models to solve customized and practical problems.
Textbook
There is no required textbook for this course.
Exercises
There will be online and written problem-solving exercises.
The exercises provide hands-on practice with new
material and with problems similar to the projects.
For the exercises, students work at their
own pace and can get help from the instructor.
Normally, exercises will be completed in teams of two students each,
with teams
starting an exercise during class time and completing it outside of
class.
Exercises are due at 11pm on their due date.
Projects
Projects help students develop a working
knowledge of the concepts presented in class. Projects are due
at 11pm on their due date.
Working with a partner on projects is optional. You may work with
a partner on as many projects as you like. However, you can only
work with a given partner on a single project during the semester.
If you want to work on projects with a partner multiple times, you
must choose a different partner for each such project. Rotating
through partners is a good way to build community in the class and is
helpful in avoiding situations where one individual feels pressured
to continue working with another.
If you would like to work with a partner, you may find your own partner
or you may use
this
shared Google document to indicate your interest in working with
a partner.
Many of the projects will be challenging. You should keep in
mind that
programming often consumes more time than expected. Start your
projects early! This will give you time to think about the
problems and ask questions if you hit an impasse.
Late Policy
Exercises and projects are due at 11pm on their due dates.
It is beneficial to student learning for course work to be completed regularly
throughout the semester. Since much of the material in the course builds off of
previous content from earlier in the course, it is helpful to keep on
schedule so that students have the necessary background to engage with the
material as it is presented in class together with their classmates.
Sometimes, however, prioritizing completion of an assignment by the
deadline may not be the right personal choice for you. To encourage
you to learn from the assignments while also affording flexibility
when it benefits your health and well-being, you may use either
of the following mechanisms to submit late
assignment (exercise and project) work without penalty:
- Self-serve 24-hour late pass: You may delay any assignment
deadline by 24 hours by submitting this
late pass
notification form before the original deadline.
There is no need for any other communication in this case.
- The form requires a brief summary of progress
(e.g., "#1 done, #2 stuck, #3 started" or "not started")
and whether you anticipate seeking support
(drop-in hours/office hours) for the assignment.
- If the 24-hour extended deadline falls during a break or
weekend, it is automatically moved to the final day of that
break or weekend.
- Custom extension: If you need to extend an assignment
deadline more than 24 hours, of if you did not submit a late pass
notification in time, you must email the instructor with an
initial timeline and plan for when and how you will complete the
assignment and report on progress.
- We will adjust the plan together to make sure it is
reasonable. The instructor may ask you to prioritize current
work first. If you need custom extensions on multiple
assignments, the instructor may ask you to check in with your
class dean to make sure you are getting the support you
need to manage your course load.
- You are never required to discuss details of your personal
circumstances with an instructor to receive an extension,
altough we are happy to lend an ear. If you choose to share,
please note that
reporting duties prevent instuctors
from holding strict confidentiality in all cases.
The above extension mechanisms are subject to the following limitations:
- The Final Project is not subject to extensions.
- Feedback and grading for work submitted under an extensions will
be completed eventually. This may take arbitrarily long,
possibly past the end of classes and exams. The likelihood and
likely magnitude of delay grow with the length of the extension.
Collaboration Policy
We believe that collaboration fosters a healthy and enjoyable
educational environment. For this reason, we encourage you to talk
with other students about the course material and to form study
groups.
For projects, students are allowed to discuss the problems with
other students and exchange ideas about how to solve them. However, there is a
thin line between collaboration and plagiarizing the work of others. Therefore,
we require that each student must compose their own
solution to each project. You may discuss strategies for approaching the
programming problems with your classmates and may receive general
debugging advice from them, but you are required to write and debug all of
your own code. Furthermore, you should never look at another
student's code. For example, it is OK to borrow code from a textbook, from materials discussed
in class, and from other sources as long as
you give proper credit. However it is unacceptable and constitutes
a violation of the Honor Code (1) to
write a program together (with someone else) and turn in two copies of the same program,
(2) to copy code written by your classmates, (3) to read another
student's code or (4) to view projects and solutions from previous terms of CS344.
In keeping with the standards of the scientific community, you
must give credit where credit is due. If you make use of an idea
that was developed by (or jointly with) others, please reference them
appropriately in your work. It is unacceptable for students to
work together but not to acknowledge each other in their
write-ups.
For exercises, you will work with a partner as part of
a two-person "team". Partners will be assigned by the instructor,
so that each student works with different partners throughout
the semester. The two team members must work closely together
on the exercise and turn in a single submission of their
exercise solutions for the team. The grade received on such a
submission will be given to both team members.
For projects, you are encouraged but not required to form a
two-person "team" with a partner. The two team members must work closely
together on the project and turn in a single submission of their
project solutions for the team. The grade received on such a submission will be given
to both team members. When partnering for projects, you can only work
with a given partner on at most one project during the semester. If you want
to work with partners on multiple projects, which is encouraged, you
must choose a different partner for each project. Rotating through
partners is a good way to build community in the class and is helpful
for avoiding situations where one individual feels pressured to
continue working with another.
Team efforts on exercises and projects are subject to
the following ground rules:
The work must be a true collaboration in which each member of the team
will carry their own weight. It is not acceptable for two
team members to split the problems in the exercise/project between them
and work on them independently. Instead, the two team members must
actively work together on all parts of the exercise/project. In particular,
almost all programming should be done with the two team members working
at the same computer. It is strongly recommended that both team members
share the responsibility of "driving" (i.e., typing at the keyboard),
swapping every so often.
Grading Policy
Your final grade will be based on a weighted average of the following components:
-
Exercises: 30%
-
Projects: 40%
-
Midterm Project: 10%
-
Final Project: 20%
At the end of the semester, we will compute a weighted average for each student and assign letter grades. In general, the mapping from numerical score to letter grades looks like this: >= 93.33 is an A, >= 90.00 is an A-, >= 86.67 is a B+, >= 83.33 is a B, >= 80.00 is a B-. >= 76.67 is a C+, >= 73.33 is a C, >= 70.00 is a C-, >= 60.00 is a D and < 60.00 is an F.
Depending on the overall performance of the class, we may adjust this mapping.
Computers and Software
All programming in CS344 will be done using the Python programming
language. We will make heavy use in the course of Python libraries such as
numpy, matplotlib, sklearn, and
TensorFlow.
We may even use MLpronto.
As software, we will use Anaconda
with Python version 3.8 or higher.
Code will be developed and shared in the course using Jupyter
notebooks.
Google Group
There is a CS344 Google Group named CS-344-01-SP25.
This group has several purposes. We will use it to make
class announcements, such as corrections to projects and
clarifications of material discussed in class. We encourage you
to post questions or comments that are of interest to students
in the course. Please do not post Python code in your messages
on the Google group! The instructor will read messages
posted to the group on a regular basis and post
answers to questions found there. If you know the answer to a
classmate's question, feel free to post a reply yourself. The
course group is also a good place to find people to join
a study group. You should plan on reading messages
from the group on a regular basis.
Masking
Masks will be optional in this class. Please note that masks are
an important tool in helping limit the spread of COVID-19 and other
respiratory illnesses. We kindly ask you to wear a mask if you feel
unwell, have sniffles, or think you may have been exposed to someone
with COVID-19 or the flu. The instructor reserves the right to ask
you to mask up or change policies on masking during the semester.
Please be respectful to members of our community (students, faculty,
staff, and others) who choose at any point in time to wear or not to
wear a face mask. Please refrain from making any judgments as
masking may help reduce allergies, prevent the spread of respiratory
illnesses, or protect immunocompromised individuals or their families.
Anonymous Feedback Form
Here is a form
for providing anonymous feedback to the instructor. You must be logged
in to a Wellesley account to use the form, however neither your email address
nor any other identifying information will be recorded.
Disabilities and Accommodations
If you have a disability or condition, either long-term or temporary, and need reasonable academic adjustments in this course, please contact Accessibility and Disability Services (ADR) to get a letter outlining your accommodation needs, and submit that letter to me. You should request accommodations as early as possible in the semester, or before the semester begins, since some situations can require significant time for review and accommodation design. If you need immediate accommodations, please arrange to meet with me as soon as possible. If you are unsure but suspect you may have an undocumented need for accommodations, you are encouraged to contact ADR. They can provide assistance including screening and referral for assessments.
Disability Services can be reached at disabilityservices@wellesley.edu, at 781-283-2434, by scheduling an appointment online at their website www.Wellesley.edu/disability , or by visiting their offices on the 3rd floor of Clapp Library, rooms 314 and 315.
Faculty Responsibilities on Disclosures of Discrimination, Harassment, and Sexual Misconduct
Pursuant to Wellesley College policy, all employees, including faculty, are considered responsible employees. That means that any disclosure of discrimination, harassment, or sexual misconduct to a faculty member will need to be shared with the College's Director of Non-Discrimination Initiatives / Title IX and ADA / Section 504 Coordinator (781-283-2451; titleix@wellesley.edu). Students who do not wish to have these issues disclosed to the College should speak with confidential resources who are the only offices at the College that do not have this same reporting obligation. On campus, confidential resources include Health Services (781-283-2810 available 24/7), the Stone Center Counseling Services (781-283-2839 available 24/7) and the Office of Religious and Spiritual Life (781-283-2685). You should assume that any person employed on campus outside of these three confidential offices has an obligation to share information with Wellesley College through the Office of Non-Discrimination Initiatives.
