TensorFlow, the open source software library developed by the Google Brain team, is a framework for building deep-learning neural networks. It is also considered one of the best ways to build in-depth learning models by people learning by machine, around the world. In deep learning models, which rely on a lot of data and computer resources, TensorFlow is used considerably.
Given its flexible architecture for easy deployment on different platforms such as CPUs, GPUs, and TPUs, TensorFlow remains one of the favorite libraries to get into ML. The huge popularity also means that tech enthusiasts are constantly looking to learn more and work more with this library. Although many tutorials, books, projects, videos, white papers, and other resources are available, we offer you these 10 free resources to get started with TensorFlow and get your concepts clear. The list is not in a specific order.
1 – Tutorial By TensorFlow (Website):
What a better source than the makers themselves! These tutorials offered by TensorFlow on their website are the perfect tools to get hands-on training. The tutorial starts with training your first neural network based on image classification and progresses further with the use of tf.keras, a high-level API used to build and train models. It also contains advanced knowledge of text classification, regression and other concepts. You can also learn to save, restore, share and recreate your work. Click here to take a tutorial.
2 – TensorFlow White Paper (paper):
This preliminary white paper by Google researchers talks about programming models and basic concepts of TensorFlow. Titled large-scale machine learning on a heterogeneous distributed system, the paper starts with a brief introduction to the concept and starts to talk extensively about examples of TensorFlow operation types, implementation, implementation in a single device and multiple devices. Along with other important concepts, this document also has a detailed schematic explanation of the concepts. Click here to read it.
3 – Stanford course on Tensorflow For Deep Learning Research (PPT):
With this course from Stanford University, you can download notes and slides that are completely focused on Tensorflow for in-depth research. The entire course is based on TensorFlow, which makes it very easy for the user to get a thorough basic understanding of TensorFlow. It also contains course material on setting up the TensorFlow, basic operations, TensorFlow optimizers, examples of image classification, reinforcement learning and much more. Click here to read it.
4 – First Contact With TensorFlow: Getting started with Deep Learning Programming by Jordi Torres (EBook):
This book by Jordi Torres, a professor and researcher at UPC and BSC, was written during a Christmas holiday to share his knowledge of TensorFlow with his students. It includes a practical approach to learning TensorFlow, starting with the basics, to understand multi-layer neural networks. It deals in detail with concepts such as linear regression, clustering and single-layer neural networks. Although it was launched with the intention of equipping its students with the basic principles of TensorFlow, it has now gone viral because it was of great value to many students and practitioners. Although it is based on the old TensorFlow release (TensorFlow-0.5.0), it is a good reading method for introduction to the topic. Click here to read it.
5 – Getting started with TensorFlow by Giancarlo Zaccone (EBook):
This is one of the best sources to help you get started with TensorFlow engine, a robust, user-friendly and customizable ML-code software library for deep learning and neural networks. It starts with an introduction to the basics, followed by details about creating programs with TensorFlow. It would help you solve mathematical concepts, ML and in-depth learning concepts along the way. Claim your free book here.
6 – Learning TensorFlow by Itay Lieder, Tom Hope, Yehezkel S. Resheff (Ebook):
This book provides an end-to-end guide to TensorFlow, which allows you to train and build neural networks for computer vision, NLP, speech recognition, general predictive analysis and others. The book emphasizes practical and practical approaches to TrumpFlow principles before you delve into deeper concepts. After reading the book you could get a thorough detail from TensorFlow, build in-depth learning models, scale up TF and implement TF in the production setting. Click here to read.
7 – TensorFlow self-study by Bharath Ramsundar (slides):
This reading slides by B Ramasundar is an excellent introduction to TensorFlow that draws many parallels between NumPy and TensorFlow codes. He has given details such as NumPy to TensorFlow dictionary, linear regression in TF, gradient calculation and others in his descriptive slides. Get to know the basics of TensorFlow with these slides. Click here to read.
8 – Deep learning with TensorFlow By Cognitive Class (online course):
Cognitive Class, an initiative of IBM, aims to democratize access to learning data science and cognitive computing. This Cognitive Class course focuses on this ideology that is free for ML enthusiasts. Something at an advanced level is suitable for anyone who is interested in improving his skills in machine learning, deep learning, and TensorFlow. It includes in-depth sources, from introduction to TensorFlow to CNN, RNN and other areas. This course with your own pace can be taken at any time. Click here to read.
9 – TensorFlow: a large-scale machine learning system (paper):
This article by Google brain researchers is a good tool to get understanding and work in TensorFlow. With different use cases and implementation of different models, this article attempts to describe the TensorFlow data stream model as opposed to existing systems. It also explains image classification, language modeling and others using TensorFlow. Click here to read.
10 – Free Github resources:
There are many sources available on Github that explain how TensorFlow works. These are from novice to advanced ML enthusiasts who want to explore TensorFlow skills. This course on Github covers, for example, the basic principles, regression, classification, clustering and other details of TensorFlow. Whereas, another Github course talks details about the simple linear model, CNN, C Keras API, and others. Here is another instance of TensorFlow resources on Github.