Deep Learning Essentials
Updated for June 2023!
Learn the foundations of deep learning and practice with training and building neural networks in PyTorch! Topics including transformers, convolutional neural networks (CNNs), and state-of-the-art generative AI models like ChatGPT and StableDiffusion.
We taught over 5000 learners from these companies:
Course taught by expert instructors
PhD at Stanford; formerly at Waymo, Microsoft
Kevin Wu, like his brother Eric, is a Ph.D. student at Stanford University. Previously, he spent time building deep learning products at a startup and has worked for Microsoft and Waymo. His current research focuses on applying AI to areas like clinical trials and genomics, as well as studying the generalizability of medical AI algorithms used in practice.
PhD at Stanford, formerly at Google
Eric Wu is a Ph.D. student at Stanford University, where he has published in major journals and conferences at the intersection of deep learning and health. Previously, he studied at Harvard and Duke University, where he taught introductory data science and deep learning courses, and worked at Google and DeepHealth, a health tech start up.
A course you'll actually complete. AI-powered learning that drives results.
Transform your learning programs with personalized learning. Real-time feedback, hints at just the right moment, and the support for learners when they need it, driving 15x engagement.
Live courses by leading experts
Our instructors are renowned experts in AI, data, engineering, product, and business. Deep dive through always-current live sessions and round-the-clock support.
Practice on the cutting edge
Accelerate your learning with projects that mirror the work done at industry-leading tech companies. Put your skills to the test and start applying them today.
Flexible schedule for busy professionals
We know you’re busy, so we made it flexible. Attend live events or review the materials at your own pace. Our course team and global community will support you every step of the way.
Each course comes with a certificate for learners to add to their resume.
15-20x engagement compared to async courses
Support & accountability
You are never alone, we provide support throughout the course.
Learn and apply skills with real-world projects.
Software engineers looking to focus on the most important deep learning topics and fundamentals
Anyone who want hands-on experience with deploying and training deep learning models.
Technically-minded individuals wanting to gain a practical intuition for current deep learning development and future progress.
In this course, we will be using Python, the dominant programming language for deep learning. A lot of the content in this course will require you to implement functions and code and will assume that you are comfortable reading and writing in Python. If you have questions about your knowledge in Python, feel free to reach out to the course staff, or consult the official Python tutorial to brush up on syntax.
Having some background in calculus, statistics, and linear algebra is also a plus. However, don't worry if you don't remember everything from that one calculus class you took in high school! We won't assume any specific knowledge, though concepts like derivatives and matrices will be touched on.
Finally, in our first week, we will have a quick primer on the basics of machine learning. If you've already had experience with machine learning before, great! Feel free to move as fast or slow as you find useful through this section. We will also include an abundance of resources beyond the scope of this class if you want to shore up your knowledge in this area in parallel.
Build a neural network classifier to power a sketch-to-emoji web app!
- A brief history of deep learning
- The basics of PyTorch
- Implement and train MLPs (multi-layer perceptrons)
- Become familiar with PyTorch and the basics of training neural networks.
Build your own GPT-like chatbot! Learn intermediate and advanced techniques for training and optimizing neural networks.
- The basics of the Transformer model
- How GPT works
- Text preprocessing for deep learning (tokenization, encoding)
- Activation functions, learning rate, and loss functions
- Stochastic gradient descent (SGD) and other optimizers
- Dive deeper into how to effectively train neural networks for various applications.
- Learn the inner workings of the powerful Transformer model that powers GPT
Dramatically improve your sketch-to-emoji app using CNNs! Then, train a model to sort mislabeled images in a Kaggle-like competition!
- Image preprocessing (normalization, loading)
- Convolutional neural networks (CNNs)
- Segmentation, object detection, and autoencoder models
- Replace MLPs with CNNs
- Experiment with different CNN architectures
Leverage powerful pre-trained models like GPT-3 and StableDiffusion to build your own deep learning enabled web app!
- Large Language Models (LLMs)
- Image-to-Text models (CLIP)
- Learn how ChatGPT and StableDiffusion/DALLE work
Course success stories
Learn together and share experiences with other industry professionals
Eric and Kevin are exceptional at being able to distill complicated subjects into easy-to-understand insights. I usually find learning subjects online to be dry and confusing, but found their teaching style to be exciting and intuitive. I would highly recommend taking this course with them.
Reasoning about the ins and outs of deep learning has been super important for my work as a machine learning engineer. Eric and Kevin really know their stuff and can explain it with contagious enthusiasm. You’ll really enjoy their course!
As a product manager at a computer-vision based start-up, I’m constantly thinking through what deep learning can (or can’t) do for my team. Eric and Kevin have been able to explain emerging research fields in digestible ways every time. Their previous experience at big tech companies like Google and Waymo also helps them speak a common “tech” language that you don’t always get with folks in academia. This course will help you in your career, whether you are working with deep learning at a high level or want to become a machine learning engineer.
Kevin and Eric are passionate machine learning experts who also happen to be great storytellers. During our time at Harvard, I’ve sought them out many times for deep learning advice, and they’ve always been very helpful in explaining cutting edge concepts with ease. I would definitely recommend anyone who has an interest in deep learning to take their course!
I'm amazed by the deep learning skills I've learned in just 4 weeks. Eric and Kevin are extremely knowledgable about the theory and application of deep learning, and really know how to explain it in a way that makes sense to anyone. I felt fully supported in my learning journey and appreciated being surrounded by other motivated peers. This course is already making a huge impact in my career as I transition into a new role as a machine learning engineer. Highly recommend this course for anyone who wants to dive into deep learning!
It was a privilege to learn from Kevin and Eric! Through their lectures, assignments and one-on-one feedback, I was able to learn deep-learning concepts that were foreign to me. They truly cared for the learning and development of each student in their class. Thank you so much!
The Deep Learning Essentials course was a fantastic course for generalist software developers like me who are interested in getting their hands dirty with deep learning. The class goes from covering the basics of network training to having you fine-tune state of the art foundation models with applications in computer vision and NLP. What I loved most about the class is that it gives you the vocabulary, experience, and confidence to either collaborate more closely with ML engineers in your company or pivot into an ML role yourself.
Joining the Uplimit Community was the best thing I did for my career. Uplimit showed me the right practical way towards Machine Learning. Now I am ML Research Fellow in NLP domain.