TensorFlow
In plain wordsGoogle's free software toolkit for building, training and running machine-learning models; it led the field after 2015 and still runs many models inside phones, browsers and company systems.
Google's open-source platform for building, training and deploying machine-learning models. At its core, TensorFlow compiles a computation into a graph of operations on tensors (multidimensional arrays), which lets the whole computation be optimized before it runs and its pieces be placed on CPUs, GPUs or TPUsTPU, abbr.: Google's own family of chips built specifically for AI, used to train and run its Gemini models and rented to other companies through its cloud., on one machine or many. TensorFlow 1.x required users to build a static graph and then run it in a session; TensorFlow 2.0 (2019) made eager execution the default, adopted KerasKeras, prop. n.: A free, beginner-friendly Python library for building neural networks from ready-made layers in a few lines of code, while a larger toolkit underneath does the heavy computing. as its high-level API, and kept graph compilation available through tf.function and the XLAXLA, abbr.: A compiler from Google that turns AI programs into fast code for chips such as TPUs and GPUs, mainly by merging many small steps into fewer, bigger ones. compiler. Around the core grew a large production ecosystem: TensorBoard for visualizing training, TensorFlow Serving for model servingmodel serving, n.: Running a trained AI model as a live service, so that apps and people can send it requests and get answers back quickly, reliably and at a sensible cost., TFX for production pipelines, TensorFlow Lite (now LiteRTLiteRT, prop. n.: Google's free software for running AI models on phones, small gadgets and microcontrollers; it was called TensorFlow Lite until 2024 and is used inside many Android and iPhone apps.) for phones and embedded devices, and TensorFlow.js for browsers. TensorFlow led framework adoption in its first years, but research moved largely to PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips. and, within Google, much new work moved to JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips..
The recommender still runs on TensorFlow Serving, though new models are prototyped in PyTorch.
Origin
Developed by the Google BrainGoogle Brain, prop. n.: Google's deep-learning research team from 2011 to 2023, where the transformer — the design behind today's chatbots — and the TensorFlow software were created. team as the successor to its internal DistBelief system and released as open source on 9 November 2015; a white paper and a 2016 OSDI paper by Martín Abadi and colleagues described its design. The name refers to tensors flowing along the edges of a dataflow graph.
Usage note
Its name helped popularize 'tensor' for any multidimensional array in machine learning, a looser usage than in mathematics and physics.
Related
- PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips.
- JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips.
- KerasKeras, prop. n.: A free, beginner-friendly Python library for building neural networks from ready-made layers in a few lines of code, while a larger toolkit underneath does the heavy computing.
- computational graphcomputational graph, n.: A map of a calculation drawn as boxes and arrows: each box is a simple operation and each arrow carries a number to the next step. AI software uses it to trace errors backward.
- LiteRTLiteRT, prop. n.: Google's free software for running AI models on phones, small gadgets and microcontrollers; it was called TensorFlow Lite until 2024 and is used inside many Android and iPhone apps.
- TPUTPU, abbr.: Google's own family of chips built specifically for AI, used to train and run its Gemini models and rented to other companies through its cloud.
- XLAXLA, abbr.: A compiler from Google that turns AI programs into fast code for chips such as TPUs and GPUs, mainly by merging many small steps into fewer, bigger ones.
- PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips.
Sources
- Abadi, M. et al. (2016). TensorFlow: A System for Large-Scale Machine Learning. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16).
- Abadi, M. et al. (2016). TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. arXiv:1603.04467.
Mentioned in
automatic differentiationautomatic differentiation, n.: A technique that lets a computer work out exactly how a program's output would change if its inputs changed slightly, by tracking every arithmetic step. It lets AI software compute training updates automatically., computational graphcomputational graph, n.: A map of a calculation drawn as boxes and arrows: each box is a simple operation and each arrow carries a number to the next step. AI software uses it to trace errors backward., CUDACUDA, prop. n.: Nvidia's software system for programming its graphics chips to do general calculations. Most AI software is built on it, which is a big reason Nvidia chips dominate AI., Google BrainGoogle Brain, prop. n.: Google's deep-learning research team from 2011 to 2023, where the transformer — the design behind today's chatbots — and the TensorFlow software were created., Jeff DeanJeff Dean, prop. n.: An American computer scientist who built much of Google's computing infrastructure, co-founded the Google Brain deep-learning team and was Google's chief scientist before leaving in 2026 to co-found a startup., KerasKeras, prop. n.: A free, beginner-friendly Python library for building neural networks from ready-made layers in a few lines of code, while a larger toolkit underneath does the heavy computing., PyTorchPyTorch, prop. n.: The most widely used free software toolkit for building and training neural networks, especially in research; programmers write ordinary Python and it handles the calculus and the graphics chips., tensortensor, n.: A block of numbers with any number of dimensions: a single number, a list, a grid, or a stack of grids. AI software stores and processes all its data this way., TPUTPU, abbr.: Google's own family of chips built specifically for AI, used to train and run its Gemini models and rented to other companies through its cloud., CaffeCaffe, prop. n.: An early free deep-learning toolkit from the University of California, Berkeley, popular for image recognition in the mid-2010s, in which networks were described in simple text files rather than code., François CholletFrançois Chollet, prop. n.: A French software engineer who created Keras, a popular tool for building neural networks, and the ARC benchmark, which tests whether AI can solve kinds of puzzles it has never seen., JAXJAX, prop. n.: A free Google library that lets researchers write mathematics in familiar Python and automatically get derivatives and very fast code for graphics chips and Google's AI chips., LiteRTLiteRT, prop. n.: Google's free software for running AI models on phones, small gadgets and microcontrollers; it was called TensorFlow Lite until 2024 and is used inside many Android and iPhone apps., ONNXONNX, prop. n.: A shared file format for trained AI models, so that a model built with one toolkit can be moved to and run by another, much as a PDF opens on any computer., TensorRTTensorRT, prop. n.: NVIDIA's software for making a trained neural network run as fast as possible on NVIDIA graphics chips, by merging and simplifying its calculations and testing which way of doing each one is quickest., TheanoTheano, prop. n.: One of the first popular free software tools for deep learning, built at a Montreal university lab; development ended in 2017, but it shaped the toolkits that replaced it., XLAXLA, abbr.: A compiler from Google that turns AI programs into fast code for chips such as TPUs and GPUs, mainly by merging many small steps into fewer, bigger ones.