We are going to still be holding lectures. However, they will be online with live streaming during the lecture (Zoom). Lecture recordings will be posted on Canvas after the lecture for students who could not participate live. Live office hours will be offered at the usual office hour times listed below. Please see the Canvas course website for more information, Zoom links for lectures, and recorded lectures.
Since lectures will be recorded, it is important to note that class recordings are confidential to the class and only for educational purposes, that they should not be shared outside the class in any form, and that any violation of this will be subject to Student Misconduct proceedings.
- Course: CS 395 T (50800) Neural Computation (aka Neuroscience for Computer Scientists)
- Semester: Spring 2020
- Location: Zoom!
- Time: TTH 3:30PM - 5:00PM
- Alexander Huth
- office hours: Tue 10:30AM - 12:00PM, Wed 10:30AM - 12:00PM
- office: ZOOM!
- email: [email protected]
Inferring what algorithms are used by existing computational systems. Using black box system identification to understand the function of real neural/brain systems. Using gradient propagation and other methods to understand the function of artificial neural networks.
By the end of this course, you should come away with an understanding of (1) the basic strategies used for inferring function from computational systems; (2) specific tools and techniques for studying the function of real and simulated neural systems; and (3) when to trust real data acquired from noisy systems.
The majority of the course will consist of lectures by the professor. For several classes, students will be asked to read and present papers to the rest of the students. Students will also be asked to give a slide presentation on the results of their final project during the last few classes of the semester.
Read the course materials. Ask questions if any topics are unclear. Be respectful of each other and the instructor. Have fun! :)
Students should have some previous programming experience (preferably in python). Discuss your situation with the instructor if you think you might not fulfill these prerequisites.
This page serves as the syllabus for this course. This syllabus is subject to change; students who miss class are responsible for learning about any changes to the syllabus.
There is no required course text book. Readings will primarily come from papers and online sources, including tutorials.
Additional required readings will be made available for download from the schedule page of the course website.
There will be no midterm or final exam.
There will be 4 homework assignments and a course project. Assignments will be posted as the semester progresses. Readings and exercises may change up to one week in advance of their due dates.
There are several components to the class grade.
-
Project (40%): There will be a group project (maximum 2 students) that will involve investigating the function of either a real computational system (using publicly available neuroscience data) or a neural network. There are three stages to this project: proposal, presentation, and final write-up.
- Proposal (5%): Before embarking on the project, each group will submit a proposal describing the topic and goal of their project.
- Presentation (20%): Each group will give a slide presentation describing the goals and results of their project.
- Write-up (15%): Each group will submit a write-up of their project.
-
Problem sets (40%): There will be 4 problem set assignments. Each assignment is worth 10% of your course grade.
-
Class participation (20%): Virtual attendance of live lecture streams is not required, but encouraged if possible. Participation in Canvas-based discussions is encouraged!
Grading scale for problem sets: problem sets will be returned with feedback less than 2 weeks after the due date.
The presentation and final project write-up will be graded based on rubrics that will be made available to you before the due dates.
Homework is due in class on the noted due date. Homework must be turned in on the due date in order to receive full credit. Homework turned in less than 1 week late will be accepted but the score will be penalized by 10%. Homework later than 1 week will not be accepted.
Late homework will also be accepted under exceptional circumstances (e.g., medical or family emergency) and at the discretion of the instructor (e.g. exceptional denotes a rare event) with no penalty. This policy allowing for exceptional circumstances is not a right, but a privilege and courtesy to be used when needed and not abused. Should you encounter such circumstances, simply email assignment to instructor and note "late submission due to exceptional circumstances". You do not need to provide any further justification or personally revealing information regarding the details.
You are encouraged to discuss problem sets with classmates, but all written submissions must reflect your own, original work. If you worked with other students on a problem set, please include their names in a statement like "I worked on this course with XX and YY" on the assignment. If in doubt, ask the instructor. Acts like plagiarism represent a serious violation of UT's Honor Code and standards of conduct:
http://deanofstudents.utexas.edu/sjs/scholdis_plagiarism.php
http://deanofstudents.utexas.edu/sjs/conduct.php
Students who violate University rules on academic dishonesty are subject to severe disciplinary penalties, such as automatically failing the course and potentially being dismissed from the University. Don't risk it. Honor code violations ultimately harm yourself as well as other students, and the integrity of the University, policies on academic honesty will be strictly enforced.
For further information please visit the Student Judicial Services Web site: http://deanofstudents.utexas.edu/sjs.
By UT Austin policy, you must notify the instructor of your pending absence at least fourteen days prior to the date of observance of a religious holy day. If you must miss a class, an examination, a work assignment, or a project in order to observe a religious holy day, I will give you an opportunity to complete the missed work within a reasonable time after the absence.
If you want to drop a class after the 12th class day, you’ll need to execute a Q drop before the Q-drop deadline, which typically occurs near the middle of the semester. Under Texas law, you are only allowed six Q drops while you are in college at any public Texas institution. For more information, see: http://www.utexas.edu/ugs/csacc/academic/adddrop/qdrop
Students with a documented disability may request appropriate academic accommodations from the Division of Diversity and Community Engagement, Services for Students with Disabilities, 512-471-6259 (voice) or 1-866-329-3986 (video phone). http://ddce.utexas.edu/disability/about/
- Please request a meeting as soon as possible to discuss any accommodations
- Please notify me as soon as possible if the material being presented in class is not accessible
- Please notify me if any of the physical space is difficult for you
Did you know that more than one-third of UT undergraduate students use the Sanger Learning Center each year to improve their academic performance? All students are welcome to take advantage of Sanger Center’s classes and workshops, private learning specialist appointments, peer academic coaching, and tutoring for more than 70 courses in 15 different subject areas. For more information, please visit http://www.utexas.edu/ugs/slc or call 512-471-3614 (JES A332).
The University Writing Center offers free, individualized, expert help with writing for any UT student, by appointment or on a drop-in basis. Consultants help students develop strategies to improve their writing. The assistance we provide is intended to foster students’ resourcefulness and self-reliance. http://uwc.utexas.edu/
The Counseling and Mental Health Center (CMHC) provides counseling, psychiatric, consultation, and prevention services that facilitate students' academic and life goals and enhance their personal growth and well-being. http://cmhc.utexas.edu/
http://deanofstudents.utexas.edu/emergency/
If you have concerns about the safety or behavior of fellow students, TAs or Professors, call BCAL (the Behavior Concerns Advice Line): 512-232-5050. Your call can be anonymous. If something doesn’t feel right – it probably isn’t. Trust your instincts and share your concerns.
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent