Deep Learning
3 Weeks
·Cohort-based Course
Master the fundamentals of deep learning and learn the techniques that power diffusion models. No prior ML experience required.
Deep Learning
3 Weeks
·Cohort-based Course
Master the fundamentals of deep learning and learn the techniques that power diffusion models. No prior ML experience required.
Course overview
Practical Deep Learning
This course is perfect for anyone looking to get into deep learning. You'll learn advanced techniques and build your own DALLE-2 model from scratch. Even if you are completely new to machine learning, this hands on course will give you the foundation you need to get started.
Who is this course for
01
You are a developer with no experience in ML, but you want to get into the field by jumping straight to the latest advances in deep learning
02
You are an ML engineer/practitioner but haven't had experience with Deep Learning.
03
You are a deep learning practitioner but haven't kept up with the latest advancements.
Key outcomes
Fundamentals and Intuitions
Understand the relevant fundamentals of deep learning that allows you to develop your own intuitions for solving problems using deep learning. Just the right amount of basics to feel confident in your own pursuits.
Ship your own models to production
Get practical understanding of how to ship your ML application in the real world. Designing the model is only one aspect of ML app development. There are many gotchas to get it working in the real world. We get you past those.
Latest and greatest
Get up to speed with how to use latest and greatest techniques in deep learning. We deep dive into transformers and variational auto encoders that power some of the most powerful models in deep learning.
Ship your own DALLE-2
Build your own DALLE-2 from scratch to get a flavor of building an end to end advanced application. Walk away with code snippets, examples that help you get started on your own project.
Deep Learning
Meet your instructor
Madhav Jha
Madhav is a computer scientist based in SF. He got his PhD on the mathematical side of computer science. He has worked as applied scientist at Amazon, as software engineer at various small and big startups, and is currently an ML engineer at Dropbox. As a CTO of an early stage AI startup, he understands and appreciates the frustrations of a software engineer trying to build something in the AI space. He strongly feels that the math behind deep learning can be simplified and armed with it software professionals can get the most out of deep learning models.
Course syllabus
01
Deep Learning Fundamentals
This module serves to be a crash course on deep learning for beginners and a quick recap for intermediate and advanced practitioners. We survey various problems that can be tackled using deep learning and help you build an intuition for problem solving using deep learning.
Ship your first deep learning model.
02
Advanced topics in deep learning
This module dives straight into one of the most exciting recent development in deep learning: Diffusion Models. Along the way we discuss two other advanced techniques transformers and variational autoencoders.
03
Ship your own DALLE-2
We go through the journey of building DALLE-2 from scratch. This gives you a hands on experience in building an advanced model end to end. Along the way we apply some advanced techniques from the previous module.
04
Modify DALLE-2 for novel use cases
Learn how to use and modify DALLE-2 for your own use case. Ultimately it is much more satisfying to scratch your own itch. We help you take your own ideas to completion where you learn to modify DALLE-2 for your own use case.
Course schedule
4-6 hours per week
September 30
Deep learning fundamentals. We kickoff the course with an introduction to deep learning. We provide enough material to do a brisk brush up on the basics over the weekend.
October 6
Deep learning recap. Advanced techniques in deep learning. Introduction to variational autoencoders and diffusion models.
October 8
Deep dive on diffusion models. We finish this week with enough material to let learners play with a toy diffusion model over the weekend.
October 13
Diffusion models roundup. Introduction to practical deep learning to ship your own models. Extensions to diffusion models.
October 15
Course conclusion and full recap of deep learning, diffusion models, and practical deep learning.
Learning is better with cohorts
Active learning, not passive watching
This course builds on live workshops and hands-on projects
Interactive and project-based
You’ll be interacting with other learners through breakout rooms and project teams
Learn with a cohort of peers
Join a community of like-minded people who want to learn and grow alongside you