AI Technology

Stanford Open-Sources Neural Network Verification Project

A Stanford Intelligent Systems Laboratory (SISL) research group has announced it is open-sourcing its NeuralVerification.jl project, which helps verify deep neural networks' training, robustness and safety results.

A Stanford Intelligent Systems Laboratory (SISL) research group has announced it is open-sourcing its NeuralVerification.jl project, which helps verify deep neural networks’ training, robustness and safety results.

Project Resource: https://github.com/sisl/NeuralVerification.jl?from=timeline#set-up-the-problem

The library is now available in GitHub and contains implementations of various methods used to verify deep neural networks. The resource divides methods to verify whether a neural network satisfies certain input-output constraints into five categories, including:

The library’s installation instructions are as follows:
image.png image.png image.png image.png Publication of the Stanford team’s related research paper is expected by the end of January 2019 at the earliest.


Author: Victor Lu | Editor: Michael Sarazen

2 comments on “Stanford Open-Sources Neural Network Verification Project

  1. Pingback: Data Science newsletter – January 16, 2019 | Sports.BradStenger.com

  2. Quality posts is the key to be a focus for the users to pay
    a quick visit the website, that’s what this site is providing.

Leave a Reply

Your email address will not be published.

%d bloggers like this: