TensorFlow was\u00a0developed by the Google Brain team for internal Google use in research and production<\/b>. The initial version was released under the Apache License 2.0 in 2015. Google released the updated version of TensorFlow, named TensorFlow 2.0, in September 2019.<\/p>\n
TensorFlow is an open source framework developed by Google researchers to run\u00a0machine learning,\u00a0deep learning\u00a0and other statistical and predictive analytics workloads. Like similar platforms, it’s designed to streamline the process of developing and executing advanced analytics applications for users such as data scientists, statisticians and predictive modelers.<\/p>\n
The TensorFlow software handles data sets that are arrayed as computational nodes in graph form. The edges that connect the nodes in a graph can represent multidimensional vectors or matrices, creating what are known as tensors. Because TensorFlow programs use a data flow architecture that works with generalized intermediate results of the computations, they are especially open to very large-scale parallel processing applications, with\u00a0neural networks\u00a0being a common example.<\/p>\n
The framework includes sets of both high-level and low-level APIs. Google recommends using the high-level ones when possible to simplify data pipeline development and application programming. However, knowing how to use the low-level APIs — called TensorFlow Core — can be valuable for experimentation and debugging of applications, the company says; it also gives users a “mental model” of the machine learning technology’s inner workings, in Google’s words.<\/p>\n
TensorFlow applications can run on either conventional\u00a0CPUs\u00a0or higher-performance graphics processing units (GPUs), as well as Google’s own tensor processing units (TPUs), which are custom devices expressly designed to speed up TensorFlow jobs. Google’s first TPUs, detailed publicly in 2016, were used internally in conjunction with TensorFlow to power some of the company’s applications and online services, including its RankBrain search algorithm and Street View mapping technology.<\/p>\n
In early 2018, Google furthered its external TensorFlow efforts by making the second generation of TPUs available to\u00a0Google Cloud Platform\u00a0users for training and running their own machine learning models. TensorFlow-based workloads are billed on a per-second basis; the Cloud TPU service initially was launched as a beta program with only “limited quantities” of the devices available for use, according to Google.<\/p>\n TensorFlow followed in the footsteps of a closed-source Google framework called DistBelief, which the company used internally to carry out unsupervised feature learning and deep learning applications based on extremely large neural networks and the\u00a0backpropagation algorithm.<\/p>\n DistBelief, which Google first disclosed in detail in 2012, was a testbed for implementations of deep learning that included advanced image and\u00a0speech recognition, natural language processing, recommendation engines and predictive analytics.<\/p>\n TensorFlow differs from DistBelief in a number of ways. Because TensorFlow was designed to be able to work separately from Google’s own computing infrastructure, its code was more easily portable for outside uses. It’s also a more general machine learning framework that isn’t as tightly focused on neural networks as DistBelief was. Moreover, it’s designed to support faster configuration and to run against the high-level APIs.<\/p>\n Google released TensorFlow as an open source technology in 2015 under an\u00a0Apache 2.0 license. Since then, the framework has gained a variety of adherents beyond Google. For example, TensorFlow tooling is supported as add-on modules to machine learning and AI development suites from IBM, Microsoft and others.<\/p>\n In early 2017, TensorFlow reached Release 1.0.0 status. That version added a specialized debugger, a domain-specific compiler for TensorFlow graphs,\u00a0Docker\u00a0container images for version 3 of the\u00a0Python\u00a0programming language and an experimental Java API. Four more releases followed during the course of 2017; a TensorFlow Lite version optimized for use on mobile and embedded devices was also introduced as a developer preview. As of February 2018, TensorFlow was up to Release 1.6.0.<\/p>\n<\/section>\n For the most part, TensorFlow applications are advanced and large-scale AI undertakings in the realms of machine learning and deep learning. In powering Google’s\u00a0RankBrain<\/a>\u00a0machine learning system, TensorFlow has been employed to improve the information retrieval capabilities of the company’s flagship search engine.<\/p>\n Google has also used the framework for applications that include automatic email response generation, image classification and optical character recognition, as well as a drug-discovery application that the company worked on with researchers from Stanford University<\/p>\n<\/section>\n Develop ML models in JavaScript, and use ML directly in the browser or in Node.js.<\/p>\n TensorFlow is a free and open-source software library for machine learning and artificial intelligence. TensorFlow, its open source community and ecosystem, and highlights some interesting TensorFlow open sourced models. The TensorFlow distributed execution engine abstracts away the many supported devices and provides a high performance-core implemented in C++ for the TensorFlow platform. Tensorflow allows developers to create a graph of computations to perform. Each node in the graph represents a mathematical operation and each connection represents data.<\/p>\n TensorFlow allows developers to create\u00a0dataflow graphs<\/em>\u2014structures that describe how data moves through a\u00a0graph<\/a>, or a series of processing nodes. Each node in the graph represents a mathematical operation, and each connection or edge between nodes is a multidimensional data array, or\u00a0tensor<\/em>.<\/p>\n TensorFlow provides all of this for the programmer by way of the Python language. Python is easy to learn and work with, and provides convenient ways to express how high-level abstractions can be coupled together. Nodes and tensors in TensorFlow are Python objects, and TensorFlow applications are themselves Python applications.<\/p>\n The actual math operations, however, are not performed in Python. The libraries of transformations that are available through TensorFlow are written as high-performance C++ binaries. Python just directs traffic between the pieces, and provides high-level programming abstractions to hook them together.<\/p>\nTensorFlow origins and releases<\/h3>\n
Applications of TensorFlow<\/h3>\n
What is TensorFlow ?<\/h2>\n
TensorFlow.js is a library for machine learning in JavaScript<\/h5>\n
How TensorFlow works aka TensorFlow architecture?<\/h3>\n