TensorFlow

TensorFlow

A machine learning software library for numerical calculation

TensorFlow is an open source machine learning software library for numerical computation. It uses nodes to represent mathematical operations and graph edges represent the multidimensional data arrays or tensors communicated between them in the data graph.

Its architecture is flexible, it allows users to extend computation to one or more CPUs or GPUs in a desktop, server or mobile device with a single API.

TensorFlow was developed by researchers and engineers of Google Brain team within Google's Machine Intelligence research organization. Its original purpose was for conducting machine learning and deep neural networks research. It was applicable in a wide variety of other domains. Google initially released it on November 9, 2015 and was solidly released on December 8, 2017.

TensorFlow is the foundation of automated software, such as DeepDream and RankBrain. RankBrain now handles a significant number of search queries for Google, replacing and supplementing traditional static algorithm-based search results.

TensorFlow is written in C++ and currently has API available in Python, C++, Java and Go. It would build an computation graph and execute symbolic differentiation.

Timeline

People

Name
Role
LinkedIn

Jeff Dean

Developer

Further reading

Title
Author
Link
Type
Date

Machine Learning with TensorFlow

Nishant Shukla

Web

TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow

Danijar Hafner, James Davidson, Vincent Vanhoucke

Academic paper

TensorFlow Distributions

Joshua V. Dillon, Ian Langmore, Dustin Tran, Eugene Brevdo, Srinivas Vasudevan, Dave Moore, Brian Patton, Alex Alemi, Matt Hoffman, Rif A. Saurous

Academic paper

TensorFlow: A system for large-scale machine learning

Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, Xiaoqiang Zheng

Academic paper

TensorFlow: A System for Large-Scale Machine Learning

Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean,Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur,Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker,Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng and Google Brain

Academic paper

Documentaries, videos and podcasts

Title
Date
Link

Companies

Company
CEO
Location
Products/Services

News

Title
Author
Date
Publisher
Description
Martin Heller
July 20, 2020
InfoWorld
Aimed at integrating models with Java applications, Deeplearning4j offers a stack of components for building JVM-based applications that incorporate AI
Ian Pointer
July 6, 2020
InfoWorld
Look no further than these excellent free resources to master the development of deep learning models using PyTorch
Terena Bell, Thor Olavsrud
March 16, 2020
CIO
Natural language processing is a branch of AI that enables computers to understand, process, and generate language just as people do -- and its use in business is rapidly growing.
Chris Merriman
November 7, 2019
http://www.theinquirer.net
GitHub's user survey reveals massive growth in open source
Pierre DeBois Founder, Zimana
Invalid Date
InformationWeek
Time series is a standard analysis, but advanced machine learning tools introduce statistical techniques for more accurate forecast models.
Golden logo
Text is available under the Creative Commons Attribution-ShareAlike 4.0; additional terms apply. By using this site, you agree to our Terms & Conditions.