TensorFlow for Machine Intelligence has been dubbed a “TensorFlow book for humans.” It’s a hands-on introduction to learning algorithms, and is for beginners who want to learn TensorFlow and Machine Learning. This book doesn’t bog you down with too much math, but it provides you with enough to help you understand TensorFlow. If you know a little machine learning (or not), and have heard about TensorFlow, but found the documentation too daunting to approach, this book is for you. The machine learning is covered after you’ve become comfortable with TensorFlow's mechanics and the core API.
If you are interested in leveling up for the new year, this book is available to KDnuggets readers for 40% off at gum.co/cgtHB/kdnuggetsholiday.
This book covers over 250 pages of material, some of which includes:
- Separate discussions on TensorFlow graphs, sessions, operations, placeholders, and variables, including their relationship to each other.
- Introduction to TensorBoard with an explanation of how to use the different classes/operations that work with TensorBoard.
- A discussion on convolutions in TensorFlow, along with all of their parameters, such as kernels, strides, padding, and data format, with examples showing the results of various kernels on images.
- A discussion on pooling layers and how to use them, along with LSTM cells, GRU cells, and bi-directional RNNs in TensorFlow.
- A complete step-by- step guide to install GPU support, by building from scratch, including walking through everything needed to download and properly install CUDA and cuDNN from NVIDIA's site.
Why use TensorFlow?
TensorFlow, a popular library for machine learning, embraces the innovation and community-engagement of open source, but has the support, guidance, and stability of a large corporation. Because of its multitude of strengths, TensorFlow is appropriate for individuals and businesses ranging from startups to companies as large as, well, Google.
What is TensorFlow currently being used for?
TensorFlow is currently being used for natural language processing, artificial intelligence, computer vision, and predictive analytics. TensorFlow, open sourced to the public by Google in November 2015, was made to be flexible, efficient, extensible, and portable. Computers of any shape and size can run it, from smartphones all the way up to huge computing clusters.
Limited holiday special for KDnuggets readers: get a 40% discount here..