Getting Started with TensorFlow
Install TensorFlow on your machine now and get started with TensorFlow today.

Wipe the slate clean and learn TensorFlow from scratch
TensorFlow Tutorial
TensorFlow Environment Setup
TensorFlow Features
TensorFlow Pros & Cons
Applications of TensorFlow
TensorFlow Architecture
TensorFlow Linear Model
Distributed TensorFlow
TensorFlow Embeddings
TensorFlow Debugger

Level up to more exciting and challenging chapters
TensorFlow Partial Differential Equations (PDE)
TensorFlow APIs
TensorBoard Graph Visualization
Wide & Deep Learning with TensorFlow
The TensorFlow MNIST Dataset
Image Recognition with TensorFlow
Audio Recognition with TensorFlow
TensorFlow Quiz- Part 1
TensorFlow Quiz- Part 2
TensorFlow Quiz- Part 3

Master new skills and evolve as an expert
TensorFlow Convolutional Neural Networks (CNN)
TensorFlow Recurrent Neural Networks (RNN)
Mandelbrot Set in TensorFlow
Single & Multiple GPUs with TensorFlow
TensorFlow for Mobile
TensorFlow Word2Vec Vector Representations
TensorFlow Performance Optimization
Security Loopholes in TensorFlow
TensorFlow Interview Questions- Part 1
TensorFlow Interview Questions- Part 2
Exploring the Library
Let’s take a look at some facts about TensorFlow and its philosophies.
TensorFlow first appeared in 2015 as an open-source software library for dataflow programming. But it being a symbolic math library, we often use it for machine learning applications like neural networks. It is safe to call it a machine learning library. The team at Google Brain developed it for internal use and released it under the Apache 2.0 open-source license on November 9, 2015. Google uses it for both research and production.
TensorFlow is written in Python, C++, and CUDA, and will work with Python, C, C++, Go, Java, JavaScript, Swift, C#, Haskell, Julia, R, Scala, Rust, and OCaml.

Google Brain