Classbaze

Disclosure: when you buy through links on our site, we may earn an affiliate commission.

Generative Adversarial Networks A-Z: State of the art (2019)

How to generate high-quality images from noise? Is it really possible? Generative Adversarial Networks were invented in 2014 and since that time it is a brea...
5.0
5.0/5
(1 reviews)
116 students
Created by

8.7

Classbaze Grade®

7.0

Freshness

9.3

Popularity

9.1

Material

How to generate high-quality images from noise? Is it really possible?
Platform: Skillshare
Video: 2h 24m
Language: English
Next start: On Demand

Best Data Science classes:

Classbaze Rating

Classbaze Grade®

8.7 / 10

CourseMarks Score® helps students to find the best classes. We aggregate 18 factors, including freshness, student feedback and content diversity.

Freshness

7.0 / 10
This course was last updated on 5/2019.

Course content can become outdated quite quickly. After analysing 71,530 courses, we found that the highest rated courses are updated every year. If a course has not been updated for more than 2 years, you should carefully evaluate the course before enrolling.

Popularity

9.3 / 10
We analyzed factors such as the rating (5.0/5) and the ratio between the number of reviews and the number of students, which is a great signal of student commitment.

New courses are hard to evaluate because there are no or just a few student ratings, but Student Feedback Score helps you find great courses even with fewer reviews.

Material

9.1 / 10
Video Score: 7.9 / 10
The course includes 2h 24m video content. Courses with more videos usually have a higher average rating. We have found that the sweet spot is 16 hours of video, which is long enough to teach a topic comprehensively, but not overwhelming. Courses over 16 hours of video gets the maximum score.
The average video length is 5 hours 35 minutes of 540 Data Science courses on Skillshare.
Detail Score: 9.3 / 10

The top online course contains a detailed description of the course, what you will learn and also a detailed description about the instructor.

Extra Content Score: 10.0 / 10

Tests, exercises, articles and other resources help students to better understand and deepen their understanding of the topic.

This course contains:

0 article.
0 resource.
0 exercise.
0 tests or quizzes.

In this page

About the course

How to generate high-quality images from noise? Is it really possible?

Generative Adversarial Networks were invented in 2014 and since that time it is a breakthrough in the Deep Learning for generation of new objects. Now, in 2019, there exists around a thousand of different types of Generative Adversarial Networks. And it seems impossible to study them all.

I work with GANs for several years, since 2015. And now I can share with you all my experience, going from the classical algorithm to the advanced techniques and state of the art models. I also added a section with different application of GANs: super-resolution, text to image translation, image to image translation and others.

This course has rather strong prerequisites:

  • Deep Learning and Machine Learning

  • Matrix Calculus

  • Probability Theory and Statistics

Here are tips for taking most from the course:

  1. If you don’t understand something, ask questions. In case of common questions I will make a new video for everybody.

  2. Use handwritten notes. Not bookmarks and keyboard typing! Handwritten notes!

  3. Don’t try to remember all, try to analyse the material.

What can you learn from this course?

Solve the Jupyter notebook, that I attached to this lesson. It is written in PyTorch. Libraries that you need:

  pip install torch seaborn matplotlib jupyter

I ask you to implement 1-dimensional GAN. Try as hard as you can. In the next lesson, I published the solution (both Jupyter and video with all explanations). And feel free to ask any questions.

Good luck:)

What you need to start the course?

There is no requirement, anyone can start this course.

Who is this course is made for?

Anybody can take this course, as it is suitable for all levels.

Are there coupons or discounts for Generative Adversarial Networks A-Z: State of the art (2019) ? What is the current price?

You can enrol in this course with a Skillshare subscription that costs $8/month, but you start with a FREE 7-day trial. You can also enrol in thousands of courses on a variety of topics with your subscription, including several Data Science courses.
The average price is $11.5 of 540 Data Science courses. So this course is -100% more expensive than the average Data Science course on Skillshare.

Will I be refunded if I'm not satisfied with the Generative Adversarial Networks A-Z: State of the art (2019) course?

There is no money-back guarantee with Skillshare, but you can start with a free one-week trial to learn without risk. With the subscription, you can download classes to your tablet or phone using the Skillshare app.

Are there any financial aid for this course?

At the moment we couldn't find any available scholarship forGenerative Adversarial Networks A-Z: State of the art (2019), but you can access more than 30 thousand classes for $8/month on Skillshare, including this one!

Who will teach this course? Can I trust Denis Volkhonskiy?

Denis Volkhonskiy has created 3 courses that got 94 reviews which are generally positive. Denis Volkhonskiy has taught 6,099 students and received a 4.1 average review out of 94 reviews. Depending on the information available, we think that Denis Volkhonskiy is an instructor that you can trust.
AI Researcher
AI Researcher
Browse all courses by on Classbaze.

8.7

Classbaze Grade®

7.0

Freshness

9.3

Popularity

9.1

Material

Platform: Skillshare
Video: 2h 24m
Language: English
Next start: On Demand

Classbaze recommendations for you