Generative Adversarial Networks - GANs Intro - New Course Release
Generative Adversarial Networks - GANs Intro - New Course Release
We are so excited to finally announce our latest Introduction to GANs course!
This course is jam-packed with a ton of info for anyone who is interested to learn about Generative Adversarial Networks. We take a multifaceted teaching approach where we learn GAN fundamentals from three different perspectives:
We'll start from the absolute basics by developing an intuition for the fundamental building blocks of GANs. Then we'll explore the math behind how GANs work, and by the end of the course, we'll be developing full GAN projects in code across two neural network APIs.
The entire course is completely self-paced, so you're free to take as little or as long as you'd like to move through and simmer on the material. Once you register, you'll have lifetime access to the course contents!
We'll discuss the registration process at the end of this episode.
What You'll Learn
A natural way to approach a new topic is to study its origin and history. Through the course, we'll have a bit of a history lesson as we explore the origins of GANs and work our way up to the progression of Deep Convolutional GANs.
Through this journey, we'll gain knowledge of (and experience with) the key components of Generative Adversarial Networks. In a later course, we'll be able to build upon this base to work our way up to current state-of-the-art models.
By taking this course, you will:
- Learn about all of the components that make up a GAN
- Intuitively understand the inherent adversarial nature of GANs
- Learn about discriminative and generative models and their relation to GANs
- Learn the intuition and math behind upsampling algorithms and transposed convolutions
- Understand the intuition and math behind BCE loss and how it's used for GANs
- Develop a fundamental understanding of the entire GAN training process
- Learn about Deep Convolutional GANs and how they're trained
- Build and train GANs in code with both PyTorch and TensorFlow
- Develop complete GAN projects in code with both PyTorch and TensorFlow
- Learn the intuition and code underlying neural network computational graphs
- Gain an understanding of important coding concepts demoed in Python
- Understand important GAN concepts via intuitive customized graphics and demos
Be sure to read the instructions for how to register for this course at the end of this blog so you can unlock access to all of the contents.
Technologies used in this course
This course will use the most popular and efficient technologies for coding and communication.
All code in this course is written in Python, an open-source programming language ranking the most popular language for data science and machine learning.
All Python code will be written within Jupyter Notebook, an intuitive web-based interactive computational environment for creating Python programs. We'll have the option to run the notebooks in a local environment or in a Google Colab environment.
By registering for the course, you will gain access to the fully written notebooks used throughout this course.
PyTorch and TensorFlow
GAN projects in this course will be completed using the top two most popular machine learning libraries:
PyTorch is a free and open-sourced machine learning library developed by Facebook's AI Research lab (FAIR), and is heavily used for training and inference of deep neural networks.
Similarly, TensorFlow is also a free and open-sourced machine learning library with a focus on deep neural networks and was developed by the Google Brain team.
Often times, one may tend to choose a single API, label it as their "favorite," and stick with it. We like the idea of learning a concept fundamentally first, and then implementing it across APIs. This not only gives us further programming experience across libraries that may be of interest to potential employers, but also strengthens our understanding of the underlying concept as we implement it in multiple ways.
This is why the code projects and demos in the course will be implemented across both PyTorch and TensorFlow from start to finish.
By registering for the course, students will gain access to the course channel of the deeplizard Discord server. This is a chat environment where you can discuss the course and other topics of interest, exchange ideas, and collaborate.
Now let's discuss the prerequisites that are required for this course.
- Basic understanding of deep learning and neural networks
- Basic coding skills
- Basic Python experience
- Neural Network API experience (recommended, not required)
If you are brand new to deep learning, then it is recommended that you start with our Deep Learning Fundamentals course first, as we'll be building on these fundamental concepts to form our understanding of GANs.
The Deep Learning Fundamentals course will teach you everything you need to know to get acquainted with all the major deep learning concepts. You can then take your newly gained knowledge from that course, and come to apply it in this GANs course.
Later in the course, we'll jump into code projects to apply what we've learned about GANs.
We'll be going step-by-step through the code when we get there, but in regards to coding prerequisites, some basic coding skills and Python experience are needed.
It's also recommended, but not necessarily required, to have experience with a neural network API, like PyTorch or TensorFlow. You can check out our courses for these APIs to get acquainted with how they work before we implement GANs in code later in the course.
Gaining access to the course
This is a premium course, and so to gain access to the contents, you must first register.
By registering for the course, you will unlock lifetime access to:
100pages of fully written corresponding lecture notes
- Custom-made quizzes following each lesson
- Download access to all code files used in this course
- The deeplizard Discord server with exclusive access to the course channel
- Practice quizzes following each lesson
- Customized visual graphics and interactive demos created solely for this course
- Regularly tested and maintained code providing updates and fixes
How to register for the course
Registration consists of two steps: creating an account on deeplizard.com and purchasing the course.
- Create a deeplizard account.
- Navigate to the Create page to create a new account.
- Enter a valid email address and password.
- Enter the verification code sent to your email address.
- Purchase the course.
- Ensure you're logged in to deeplizard.com.
- Browse to the course page.
- Click the Enroll button.
- Agree to the course terms and conditions.
- Enter your payment details. If you have a discount code, you may enter it here.
- Upon successful payment, the course will become unlocked, and you may view the full contents. You will also receive a Welcome email with instructions to download course code files and join the Discord.
Committed by on