About TensorFlow Specialization: Advanced Techniques course
О TensorFlow
TensorFlow is an end-to-end open source platform for machine learning. It has a rich, flexible ecosystem of tools, libraries, and community resources that makes it easy for researchers to advance the cutting edge of ML and for developers to easily build and deploy ML-enabled applications. TensorFlow is widely used in machine learning applications such as voice recognition and detection, Google Translate, image recognition and natural language processing.
About this specialization
Expand your knowledge of functional APIs and build exotic non-sequential model types. Learn how to optimize training in a variety of environments with multiple processors and chip types, and become familiar with advanced computer vision scenarios such as object detection, image segmentation, and convolution interpretation. Explore generative deep learning, including ways AI can create new content, from style transfer to auto-encoding, VAE, and GANs.
About you
This specialization is designed for software and machine learning engineers who have a basic understanding of TensorFlow and want to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.
Looking for where to start? Master the basics with
professional certificate DeepLearning.AI TensorFlow Developer.
Ready to deploy your models to the world? Find out how to get started with
TensorFlow: Data and Deployment Specialization.
Applied Learning Project
In this specialization, you will gain hands-on knowledge and hands-on training in advanced TensorFlow techniques such as style transfer, object detection, and generative machine learning.
Course 1: Understand basic functional API fundamentals and build exotic non-sequential model types, custom loss functions, and layers.
Course 2: Learn how optimization works and how to use GradientTape and Autograph. Optimize training across multiple environments with multiple processors and chip types.
Course 3: Practice object detection, image segmentation, and visual interpretation of convolutions.
Course 4: Explore generative deep learning and how AI can create new content, from style transfer through autoencoding and VAE to generative adversarial networks.
