Introduction to Deep Learning & Neural Networks

An interactive text-based course to learn the principles behind deep learning architectures. Explore the theory and intuition behind the algorithms and build your models with Pytorch.

Learn Deep Learning

with AI Summer

This course is an accumulation of well-grounded knowledge and experience in deep learning. It provides you with the basic concepts you need in order to start working with and training various machine learning models.

You will cover both basic and intermediate concepts including but not limited to: convolutional neural networks, recurrent neural networks, generative adversarial networks as well as transformers.

After completing this course, you will have a comprehensive understanding of the fundamental architectural components of deep learning. Whether you’re a data and computer scientist, computer and big data engineer, solution architect, or software engineer, you will benefit from this course.

Understand the most popular Deep Learning models

Get a solid grasp on the mathematics and the intuition behind the algorithms

Gain a good experience with Deep Learning programming and Pytorch

Learn using a hands-on approach and build your models in the browser

Understand the fundamental Deep Learning architectures.


Neural Networks

Understand the basic principles behind Neural Networks, Gradient Descent and Pytorch.


Training Neural Networks

Familiarize yourself with optimization algorithms, activation functions and train your first model.


Convolutional Neural Networks

Learn about convolution, how it is used in convolutional networks and advanced concepts such a batch normalization and skip connections.


Recurrent Neural Networks

Build RNNs and LSTMs from scratch and get to know how to use them for time series analysis and prediction.



Learn the theory and mathematics behind Autoencoders and Variational Autoencoders.


Generative Adversarial Networks

Dive into adversarial attacks, GANs and explore how to train one using Pytorch.


Attention and Transformers

Discover attention-based models, the Transformer architecture and how they revolutionalized the natural language processing field.


Graph Neural Networks

Process and analyze graph data with Graph Neural Networks.

Learn the intuition and mathematics using a text-based approach offers strictly interactive text-based courses focusing on hands-on experience without the hassle of videos. That way you speed up the learning process, keep notes without pausing the video and access anything fast.

Develop your models using interactive code editors

You can quickly jump on coding using the provided live coding environements and jupyter notebooks. No setup, no installing dependencies. Program and execute your code straight in your browser.

Experiment with Jupyter notebooks

Build and train your models in Jupyter notebooks with zero setup. Experiment with different hyperparameters, optimization algorithms and architectures all in your browser.

Test your knowledge with coding challenges and quizzes

You can test your understanding using interactive quizzes, easy leetcode-style coding challenges with solutions. In the end, you will also need to pass a final assesment finish the course.

Get started with Deep Learning

Enroll now

But why 100% text and no videos?

We believe that text is more effective and faster for learning advanced concepts such as Deep Learning.

Text is faster than videos

Learn at your own pace

Active learning and hands-on experience

Revisit lessons and skip others easily

Keep notes without pausing the video

Copy paste the code in your own environment

How this course came into life?

For more than a year, we wrote weekly deep learning articles for the AI Summer blog. One day we came across and we had this awesome idea. To combine some of them into a single resource and give you the ability to learn Deep Learning by doing. That's why 70% of the course's content can be found in our blog for free. So if you can't afford this course, you are more than welcome to read our free articles. If on the other hand you want to support us for our efforts and learn using a highly interactive platform, you can spend a few bucks.


What do I need to know before getting started?

Because deep learning is an advanced field, you will probably need

  • A solid background on Mathematics such as Linear Algebra, Probabilities and Calculus
  • Good programming experience with Python
  • Some knowledge of Machine Learning
How much is the course's cost?

You can purchase it for one year with $39 or you can subscribe to and get access to all the course with a small monthly fee

Can I find the solutions for the coding exercises?

All coding exercises and jupyter notebooks can be found on our Github repository

What libraries and tools will I use?

You will write your code in Pytorch and perhaps you will need to use Numpy.

Can I track my progress?

Of course, every lesson you complete is saved in your profile.

Can I preview the course before I buy?

Yes, you can view a few selected lessons beforehand.

Can I request my money back after I buy?

If you purchased the course within 7 days, you can request a refund by sending us an email with your order ID at

You can find the order ID in the confirmation email that you received or transactions.

Note that this return policy only applies to individual course subscriptions and NOT unlimited access subscriptions.

Can I use the code in my projects?


Can I download the content and share it with my friends?

I'm afraid not. prohibits to download any content and reshare it.

I have another question. How can I reach you?

Feel free to use the contact form on the Contact page or email us at,