TensorFlow Application Development Using TensorFlow 2-in-1

MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz, 2 ChLanguage: English | Duration: 4h 20m | Size: 2.4 GB

Create deep learning models for your mobile applications by leveraging the potential of AI with TensorFlow.

What you'll learn

Develop AI systems using different machine learning models

Deploy TensorFlow models on iOS and Android platforms

Design solutions to real-life computer vision problems to tackle typical challenges when developing real-life applications

Explore generative models and how they generate information from random noise.

Optimize machine learning models for better performance and accuracy

Understand different deep learning models for computer vision

Requirements

Basic knowledge of TensorFlow is assumed

Basic understanding of machine learning concepts will be useful

Description

The flexible architecture of TensorFlow allows you to create and deploy deep learning and deep reinforcement learning models for building intelligent, real-world applications. TensorFlow facilitates AI to build and train systems, in particular, neural networks.

This comprehensive 2-in-1 course is a hands-on approach to problem-solving. Gain practical knowledge by coding TensorFlow models to solve real-life problems such as gesture or voice recognition. You’ll also learn to deploy TensorFlow models on mobile devices.

Contents and Overview

This training program includes 2 complete courses, carefully chosen to give you the most comprehensive training possible.

The first course, Hands-on Artificial Intelligence with TensorFlow, covers a practical approach to deep learning and deep reinforcement learning for building real-world applications using TensorFlow. This course will teach you how to combine the power of Artificial Intelligence and TensorFlow to develop some exciting applications for the real world. You will then be taken through techniques such as reinforcement learning, heuristic searches, neural networks, Computer Vision, OpenAI Gym, and more in different stages of your application.

The second course, Hands-on TensorFlow Lite for Intelligent Mobile Apps, covers application of Machine Learning models in real- in mobile devices with the new and powerful TensorFlow Lite. This course will teach you how to solve real-life problems related to Artificial Intelligence—such as image, text, and voice recognition—by developing models in TensorFlow to make your applications really smart. You will understand what Machine Learning can do for you and your mobile applications in the most efficient way. With the capabilities of TensorFlow Lite you will learn to improve the performance of your mobile application and make it smart.

By the end of the course, you’ll be able to implement AI in your mobile applications as well as build intelligent apps by leveraging the full potential of Artificial Intelligence with TensorFlow.

About the Authors

SaikatBasak is currently working as a machine learning eeer at Kepler Lab, the research & development wing of SapientRazorfish, India. His work at Kepler involves problem-solving using machine learning, researching and building deep learning models. Saikat is extremely passionate about Artificial intelligence becoming a reality and hopes to be one of the architects of the future of AI.

Juan Miguel Valverde Martinez is a Deep Learning, Computer Vision and TensorFlow enthusiast, with an MSc in IT and Cognition from the University of Copenhagen. His main interests are Computer Vision and Medical Image Analysis, and he has recently been more interested in Adversarial Training and Natural Language Processing. In his free , he likes to read papers and research. In addition to Computer Science, he also enjoys learning languages and cooking, especially Mediterranean and Asian dishes.

Who this course is for

Developers and aspiring Data Science professionals who would like to develop their AI techniques to create smart and robust applications.

Mobile developers who want to make their mobile applications smart with TensorFlow to solve machine learning, computer vision or deep learning problems such as data prediction, visual or audio recognition, and more.