In this course, you will: a) Learn neural style transfer using transfer learning: extract the content of an image (eg. swan), and the style of a painting (eg. cubist or impressionist), and combine the content and style into a new image. b) Build simple AutoEncoders on the familiar MNIST dataset, and more complex deep and convolutional architectures on the Fashion MNIST dataset, understand the difference in results of the DNN and CNN AutoEncoder models, identify ways to de-noise noisy images, and build a CNN AutoEncoder using TensorFlow to output a clean image from a noisy one. c) Explore Variational AutoEncoders (VAEs) to generate entirely new data, and generate anime faces to compare them against reference images. d) Learn about GANs; their invention, properties, architecture, and how they vary from VAEs, understand the function of the generator and the discriminator within the model, the concept of 2 training phases and the role of introduced noise, and build your own GAN that can generate faces. The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture, and gives them the tools to create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.
Excellent course. The only reason I don't opt to 5-rate it is because, coming from completing courses by Andrew Ng, I kind of wanted a more mathematics/theory- driven course.
excellent course, which gives a very good insight to modeling with advanced tecnhiques!!
Excellent course.I really appreciated to have a quiz and an assignment each week.Thanks to all the contributors.
A very professional course with an excellent instructor.
Although the VAE module was a bit difficult, I found this course helpful to refine my deep learning knowledge.
Clear explanation on all generative methods. However, I find it too short. The course can be longer and include more generative methods.
The best course for learning the implementation of GANs, stacked and variational autoencoders.
A wonderful course to learn on how we can achieve the output from the input itself using VAE. Thanks for building this course!
Very good course, I learned many new and interesting things from here. The quizzes and labs are quite challenging.
Excellent course - Indepth knowledge delivered by one of the top-developers in an engaginand challenging manner. Superb. Would definitely recommend.
Great as all other courses in this set of specializations! Thank you!
Really good content covering the surface of lot of advanced topics.
Showing: 20 of 50
Excellent course. Highly recommended. Please make a separate course on GAN. Use TensorFlow instead of PyTorch
The session on VAE's was interesting, If I could make a suggestion, I would add other generative models, such as Deep Belief Nets, and show how the generated data change from DBNs to VAES to GANS with the same dataset. That would give students a better idea of the tradeoffs involved in each of them.
Outstanding course that deals with complex topics in Deep Learning explained in short yet precise manner and flawlessly executed.
Excellent course.
I really appreciated to have a quiz and an assignment each week.
Thanks to all the contributors.
Excellent course. The only reason I don't opt to 5-rate it is because, coming from completing courses by Andrew Ng, I kind of wanted a more mathematics/theory- driven course.
Clear explanation on all generative methods. However, I find it too short. The course can be longer and include more generative methods.
Really good content covering the surface of lot of advanced topics.
The course will give you an introduction to autoencoders, some extension to neural style transfer from Deeplearning specialization and last week was brief introduction to GANs. Everything is well explained and knowledge from assignments may be re-used during your own projects. After the whole specialization you can't say that it didn't give you an opportunity to learn how to use Tensorflow. However, it's focused mostly on image processing so if you dislike this topic - it's not for you.
really great course, it showed how VAE and AutoEncoders work, also touched on the topic of GANs, the best part was applying what's learned during the whole specialization on building difficult and complicated models from scratch.
Sessions, labs and assignment are really very good from advance programming in Tensorflow perspective. Additional or optional sessions on KL divergence, reconstruction loss would have helped learners a lot.
Excellent course - Indepth knowledge delivered by one of the top-developers in an engaginand challenging manner. Superb. Would definitely recommend.
Great Course. It would be better to have Capstone Project and Peer Review Process to prove that we are actually able to apply all these techniques.
A wonderful course to learn on how we can achieve the output from the input itself using VAE. Thanks for building this course!
Amazing Course.
I Loved It
It is very interesting and by the way you obtain the outcomes you can see inmediately your advances!
Very Instructive! Laurence is a great teacher explaining. I was able to understand CNN / GANS in a unique and smooth way
Very good course, I learned many new and interesting things from here. The quizzes and labs are quite challenging.
Although the VAE module was a bit difficult, I found this course helpful to refine my deep learning knowledge.
This course was fantastic! Laurence and DeepLearning.ai team did great job. Definitely recommended.
excellent course, which gives a very good insight to modeling with advanced tecnhiques!!
Great as all other courses in this set of specializations! Thank you!