Syllabus

Last updated May 31, 2023

Objective

This course is meant to be a practical introduction to deep learning methods for biological data. Our goal is to provide you with the tools necessary to apply these methods to your own data. We also want to give you enough conceptual knowledge to know what to do when things do not work.

The course will be have two primary components.

1. Lectures will be high level and conceptual.

2. Recitations will be hands on demonstrations of best practices.

3. Jupyter Notebooks will serve as practical guides to the concepts introduced in lecture.

Course Instructor

Professor David Van Valen
vanvalen[at]caltech[dot]edu
Office Hours: Available by request.

Teaching Assistants

Morgan Schwartz
msschwartz[at]caltech[dot]edu
Office Hours: Available for sign up through Calendly

Rohit Dilip
rdilip[at]caltech[dot]edu
Office Hours: Available for sign up through Calendly.

Course Communication

This website will serve as the central hub for the course. Canvas will be used for distributing announcements and collecting any submissions for the course. Discussion threads have been established for course questions and coding problems or bugs.

Lectures

Lectures will be held Tuesday/Thursday 1-2:30 PM in Chen 130. Lectures notes will be linked on the Course Schedule after the lecture.

Recitations

Recitations will be held once a week on Wednesdays from 5 to 6pm in Chen 240a.

Grading

Guest lecture attendance is mandatory. If you have an unavoidable conflict, you must reach out to the TAs beforehand.

Assignment	Points	Due Date
Assignment 1: Cell Classification	125	4/21
Assignment 2: Preliminary Proposal and Dataset Exploration	150	4/28
Assignment 3: Project Proposal	150	5/5
Assignment 4a: Celltype classification redux	125	5/12
Assignment 4b: Protein sequence modeling	125	5/12
Assignment 5: Progress Report	50	5/19
Final Presentation	100	Seniors/Grads: 6/9; Undergrads: 6/16
Final Report	300	Seniors/Grads: 6/9; Undergrads: 6/16
Guest lecture attendance	TBD
Class Total	1000

Class Project

The majority of the class will be graded based on a project that will span the duration the course. You should begin thinking about the project you would like to pursue during the first few weeks of the course. Your class project serves as an opportunity for hands on exploration of using deep learning on a biological question of your choice. You may work on your own or in a group. There will be a series of brief assignments leading up to the final submission.

Your project for this course will require writing a substantial amount of code to implement a deep learning model. The official language/package for this class is Python and the instructors will be able to provide assistance with debugging your code. You may choose to work with another language or package, but we will not be able to provide any support.

The following assignments are directly related to your project:

• Assignment 2: Preliminary Proposal and Dataset Exploration

• Assignment 3: Project Proposal

• Assignment 5: Progress Report

• Final Presentation

• Final Report

You are welcome to use your own data for your project, but you may also select from any publicly available dataset. You can explore our collection of Publicly Available Datasets.

Late Assignments

Late assignments will lose 10% for each day late. Extensions for due dates can be granted by the TA in light of extenuating circumstances. Please reach out prior to the deadline.

Collaboration Policy

Collaboration on homework assignments is encouraged. You may consult outside reference materials, other students, the TA, or the instructor, but you cannot consult homework solutions from prior years, and you must cite any use of material from outside references. All solutions that are handed in should be written up individually and should reflect your own understanding of the subject matter at the time of writing. Python scripts and plots are considered part of your write-up and should be done individually (you can share ideas, but not code).

Academic Integrity

Caltech’s Honor Code: “No member of the Caltech community shall take unfair advantage of any other member of the Caltech community.”

Understanding and Avoiding Plagiarism: Plagiarism is the appropriation of another person’s ideas, processes, results, or words without giving appropriate credit, and it violates the honor code in a fundamental way. You can find more information at: http://writing.caltech.edu/resources/plagiarism.

All instances of plagiarism or other academic misconduct will be referred to the Board of Control for undergraduates. For graduate students, contact the Graduate Office.

Wellness Policy

While COVID-19 remains a concern, all members of the Caltech community, including students and others, are required to promptly report. to the Institute if they have become ill with COVID-like symptoms or have been exposed to someone who has tested positive for COVID-19. Furthermore, any individual, regardless of vaccination status, who is ill or has been exposed to COVID-19 should stay home or return home if they have already reported on-site (including not attending class or other meetings in person), and report their status through the Caltech COVID-19 Reporting Application. Individuals who have reported their status through the COVID-19 Reporting Application will receive personal follow up and guidance from Student Wellness Services on next steps. For additional information on the Institute’s COVID-19 preventative health measures and requirements, visit the Caltech Together website.

If you would like to ask about flexibility with coursework for a temporary or minor wellness issue, please contact Rohit Dilip directly. The Deans’ Office, Student Wellness Services (SWS) and Caltech Accessibility Services for Students (CASS) are available to help you with illness and health conditions that may impact your coursework.

Students with Documented Disabilities

Students who may need an academic accommodation based on the impact of a disability must initiate the request with Caltech Accessibility Services for Students (CASS). Professional staff will evaluate the request with required documentation, recommend reasonable accommodations, and prepare an Accommodation Letter for faculty dated in the current quarter in which the request is being made. Students should contact CASS as soon as possible, since timely notice is needed to coordinate accommodations. For more information: https://cass.caltech.edu/, cass@caltech.edu. If you are having difficulties with access or other challenges in the class you think might be related to a disability, but do not yet have a diagnosis, please feel free to reach out to CASS to learn more about resources.