Machine learning models can be optimised in several different ways.

One such type of optimisations is focused on reducing the number of parameters and operations involved by removing the connections between neural layers.

This pruning API is built on top of Keras making it easy for developers to apply it to any Keras training program.

Weight pruning has several advantages, the most immediate being disk compression. A 90% sparse model can be compressed from 12MB to nearly 2MB. Visit the website to get a complete picture of how it works.

TO DO: Use TensorFlow Model Optimization Toolkit to optimize neural network

Related

Still a handsome devil: Raspberry Pi 4

For those who don’t know, Raspberry Pi is a low cost… 

  • 9

Why Bolivian clocks run anti-clockwise

Clockwise motion as forward movement of time is so… 

  • 9

A real time whiteboard for collaborative…

WBO is a free online collaborative whiteboard that allows… 

  • 10

The best, free courses for deep and machine…

Fast.ai provides free and ad-free online courses on deep… 

  • 10

Transform your noob sketches to stunning…

Researchers at NVIDIA are always at it, when it comes to AI… 

  • 10

Make better product decisions with this…

With shifting mindset in the internet industry, product… 

  • 11

Analysing Iris data set with Python

The Iris flower data is a data set introduced by the… 

  • 9

A fast, free and secure way to encrypt your…

The javascript app hat.sh provides secure file encryption… 

  • 10

How to create the perfect remote working…

Remote work, while appears to be a great option, comes… 

  • 9

Discover interesting things to explore and do

We curate authentic and awesome content. Sign up for our newsletter for your daily dose of inspiration !