Skip to content

Synchronous Online Course

We offered a paid cohort experience with the following additions to the lecture and lab materials released publicly:

  • Slack workspace for learners, instructors, and teaching assistants
  • Weekly graded assignment
  • Capstone project reviewed by peers and staff
  • Certificate of completion

Check out the original announcement page.

How do I know if I am in this course?

If you registered and received an email receipt from Stripe, you're in, and should have been added to our Slack workspace on February 1.

Please email us if you have a Stripe receipt but aren't in our Slack.

Teaching Assistants

This course is only possible with the support of our amazing TAs:

  • Head TA James Le runs Data Relations for Superb AI and contributes to Data Journalism for Snorkel AI, after getting an MS in Recommendation Systems at RIT.
  • Daniel Cooper is a machine learning engineer at QuantumWork, SaaS for recruiters.
  • Han Lee is a Senior Data Scientist at WalletHub. Prior to that, he worked on various DS, MLE, and quant roles. Previously, he co-managed TEFQX.
  • Nadia Ahmed is a machine learning researcher with The Frontier Development Lab and Trillium Technologies in remote sensing for severe weather and flood events.
  • Andrew Mendez is a Senior Machine Learning Engineer at Clarifai, developing large scale computer vision and machine learning systems for the public sector. Previously he was a ML Engineer at CACI.
  • Vishnu Rachakonda is a Machine Learning Engineer at Tesseract Health, a retinal imaging company, where he builds machine learning models for workflow augmentation and diagnostics in on-device and cloud use cases.
  • Chester Chen is the Director of Data Science Engineering at GoPro. He also founded the SF Big Analytics Meetup.


While we post lectures once a week starting February 1, the first four weeks are review lectures -- stuff you should already know from other courses.

On March 1, we get to the Full Stack content, and you will begin doing weekly assignments, discussing in Slack, and thinking about their course project.


All learners, instructors, and TAs will be part of a Slack workspace. The Slack community is a crucial part of the course: a place to meet each other, post helpful links, share experiences, ask and answer questions.

On Monday, we post the lecture and lab videos for you to watch. Post questions, ideas, articles in Slack as you view the materials.

On Thursday, we go live on Zoom to discuss the posted questions and ideas. We have two 30-min slots: 9am and 6pm Pacific Time. We will send everyone a Google Calendar invite with the Zoom meeting information.

You have until Friday night to finish the assignment via Gradescope, which will be graded by next Tuesday, so that you have prompt feedback.

Labs are not graded and can be done on your own.


The final project is the most important as well as the most fun part of the course. You can pair up or work individually. The project can involve any part of the full stack of deep learning, and should take you roughly 40 hours per person, over 5 weeks.

Projects will be presented as five-minute videos and associated reports, and open sourcing the code is highly encouraged. All projects will be posted for peer and staff review.

The best projects will be awarded and publicized by Full Stack Deep Learning.

If you want to find a partner, please post in the #spring2021-projects Slack channel with your idea or just that you're available to pair up.

Project proposals are due on Gradescope a few weeks into the course.

Please read more information about the projects.


Those who complete the assignments and project will receive a certificate that can, for example, be displayed on LinkedIn.

Time Commitment

On average, expect to spend 5-10 hours per week on the course.

We are excited to share this course with you for free.

We have more upcoming great content. Subscribe to stay up to date as we release it.

We take your privacy and attention very seriously and will never spam you. I am already a subscriber