What is TensorFlow?
TensorFlow is an open source software library for machine learning developed by Google – Google Brain team. Name TensorFlow derives from the operations which neural networks perform on multidimensional data arrays, often referred to as “tensors”. It is using data flow graphs, and is capable of building and training variety of different machine learning algorithms and deep neural networks, but it is general enough to be applicable in a wide variety of other domains as well. Flexible architecture allows to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.
TensorFlow is Google Brain’s second generation machine learning system, released as open source software in 2015. TensorFlow is available on 64-bit Linux, MacOS, and mobile computing platforms including Android and iOS. TensorFlow provides a Python API, as well as C++, Haskell, Java and Go APIs. In 2016 Google announced Tensor Processing Unit (TPU), a custom built for machine learning programmable AI accelerator designed to provide high throughput of low-precision arithmetic.
Among a variety of applications for which TensorFlow is used and listed in the TesnsorFlow website are:
RankBrain – A large-scale deployment of deep neural nets for search ranking on Google.
Inception Image Classification Model – highly accurate computer vision models, starting with the model that won the 2014 Imagenet image classification challenge.
SmartReply – Deep LSTM model to automatically generate email responses
Massively Multitask Networks for Drug Discovery – A deep neural network model for identifying promising drug candidates.
On-Device Computer Vision for OCR – computer vision model to do optical character recognition to enable real-time translation.