TensorFlow

TensorFlow

TensorFlow was originally developed by the researchers and engineers working on the Google Brain team for both research and production at Google. TensorFlow is general, flexible, portable, easy-to-use, and completely open source. It can run on one or more CPUs and GPUs in a desktop, server, or mobile device with a single API. It is available on 64-bit Linux, macOS, Windows and mobile computing platforms including Android and iOS. TensorFlow has extensive built-in support for deep learning.

TensorFlow is aimed at the development of machine learning systems that require heavy numerical computation, like artificial neural networks (ANNs). The trouble with these systems is that they consist of millions of numbers - too many for people to sift through and make sense of.

It is represented using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. It is mainly used for conducting deep neural networks research to detect and decipher patterns and correlations, similar to (but not the same as) human learning and reasoning.