Getting Started with TensorFlow for Deep Learning [Video]

More Information
Learn
  • Properly understand the meaning of deep learning
  • Train a neural network and understand the often complicated process of backpropogation.
  • Create datasets in the correct format for use with TensorFlow—a key step when it comes to training your own models.
  • Create your own neural network architecture in TensorFlow using Keras, allowing you to define any architecture for your own needs.
  • Get accustomed to convolutional neural networks and understand why they are so powerful for image classification.
  • Use the TensorFlow ObjectDetection API to classify and localize objects in an image
About

We will not only get you up-and-running with deep learning, but also equip you with the skills to implement your own neural networks and apply them to the real world.

We will use TensorFlow, an efficient Python library used to create and train our neural networks. You'll learn the skills to implement their architecture quickly and efficiently without having to deal with minutiae.

You can rely on our expert guidance while learning the basic theory, backed up with relevant examples. We provide examples of neural networks, which you can use to highlight the key features. We then build up to more advanced networks. You'll learn to utilize a Convolutional Neural Network to classify images of handwritten text and then take your CNN further to perform object detection and localization in an image.

This course will quickly get you past the fundamentals of TensorFlow; you'll go on to more exciting things such as implementing a variety of image recognition tasks. All the code and this course's supporting files are available on GitHub at - https://github.com/PacktPublishing/Getting-Started-with-TensorFlow-for-Deep-Learning-

Style and Approach

This course will breeze through some essential textbook knowledge when it comes to machine learning. Following a brief math section, we get started with deep learning straight away.

Features
  • Take the theory and apply it to create networks to classify sentence polarity, recognize handwritten digits, and then locate objects in an image.
  • Learn the fundamentals of deep learning, to get a strong foundation.
  • Combines an easily understandable explanation of deep learning coupled with a handful of implementations using the TensorFlow package.
Course Length 2 hours 45 minutes
ISBN 9781788475518
Date Of Publication 30 Nov 2018

Authors

Tom Joy

Colibri Digital is a technology consultancy company founded in 2015 by James Cross and Ingrid Funie. The company works to help its clients navigate the rapidly changing and complex world of emerging technologies, with deep expertise in areas such as big data, data science, machine learning, and cloud computing. Over the past few years, they have worked with some of the world's largest and most prestigious companies, including a tier 1 investment bank, a leading management consultancy group, and one of the World's most popular soft drinks companies, helping each of them to make better sense of its data and process it in more intelligent ways. The company lives by its motto: Data -> Intelligence -> Action.

Tom Joy is studying for a PhD at the University of Oxford in the field of Semantic SLAM, which is the process of simultaneously localizing a robot in space; producing a map/understanding of the surrounding area whilst also detecting and delineating objects in 3D space. Achieving this requires a high level of competency in computer vision, machine learning, and optimization.

Tom has extensive experience in computer vision and machine learning, having taken several internships and placements over the course of his degree and spent time in industry prior to starting his PhD. He is a big advocate of explaining concepts simply and in a clear and concise manner; he strives to obtain and provide a comprehensive understanding of all relevant methods to the task at hand.