Learning TensorFlow

Roughly inspired by the human brain, deep neural networks trained with large amounts of data can solve complex tasks with unprecedented accuracy. This practical book provides an end-to-end guide to TensorFlow, the leading open source software library that helps you build and train neural networks for computer vision, natural language processing (NLP), speech recognition, and general predictive analytics.Authors Tom Hope, Yehezkel Resheff, and Itay Lieder provide a hands-on approach to TensorFlow fundamentals for a broad technical audiencefrom data scientists and engineers to students and researchers. Youll begin by working through some basic examples in TensorFlow before diving deeper into topics such as neural network architectures, TensorBoard visualization, TensorFlow abstraction libraries, and multithreaded input pipelines. Once you finish this book, youll know how to build and deploy production-ready deep learning systems in TensorFlow.Get up and running with TensorFlow, rapidly and painlesslyLearn how to use TensorFlow to build deep learning models from the ground upTrain popular deep learning models for computer vision and NLPUse extensive abstraction libraries to make development easier and fasterLearn how to scale TensorFlow, and use clusters to distribute model trainingDeploy TensorFlow in a production setting

Itay Lieder is an applied researcher in Machine Learning and Computational Neuroscience and a PhD student at the Hebrew University, in collaboration with the Gatsby Computational Neuroscience Unit at UCL, studying the human perception with massive crowd-sourcing experiments on Amazon Turk. His current work focuses on predicting and understanding the way humans react to sounds (e.g. music), via multiple online interactive experiments. He has worked for large international corporations, leading Deep Learning R&D in text analytics and web mining for sales and marketing.