Deep Neural Network implemented in pure SQL over BigQuery

Deep Neural Network implemented in pure SQL over BigQuery

  • March 14, 2018
Table of Contents

Deep Neural Network implemented in pure SQL over BigQuery

In this post, we’ll implement a deep neural network with one hidden layer (and ReLu and softmax activation functions) purely in SQL. The end-to-end steps for neural network training including the forward pass and back-propagation will be implemented as a single SQL query on BigQuery. As it runs on Bigquery, in effect we are performing distributed neural network training on 100s to 1000s of servers.

Sounds cool! right?

Source: towardsdatascience.com

Tags :
Share :
comments powered by Disqus

Related Posts

Open Source Neural Network Synthesizer

Open Source Neural Network Synthesizer

NSynth Super is part of an ongoing experiment by Magenta: a research project within Google that explores how machine learning tools can help artists create art and music in new ways. Technology has always played a role in creating new types of sounds that inspire musicians—from the sounds of distortion to the electronic sounds of synths. Today, advances in machine learning and neural networks have opened up new possibilities for sound generation.

Read More
A history of machine translation from the Cold War to deep learning

A history of machine translation from the Cold War to deep learning

Read More
Behind the Motion Photos Technology in Pixel 2

Behind the Motion Photos Technology in Pixel 2

Background motion estimation in motion photos. By using the motion metadata from Gyro and OIS we are able to accurately classify features from the visual analysis into foreground and background.

Read More