Home
Services
Services
Develop your AI maturity with tailored services
01
AI & data strategy
02
Data engineering
03
Educational workshop
04
Tailored ML solutions
05
AI team extension
06
ML deployment & operations
Industries
01
Chemicals
02
CPG
03
Banking
04
Logistics
05
Manufacturing
06
Pharma
07
Utilities
Industries
Industries
Ensure the success of your AI transformation
01
Chemical
02
Consumer Packaged Goods
03
Financial Services
04
Logistics
05
Manufacturing
06
Pharmaceuticals
07
Utilities
About
Our valuesOur story
Our team
Blog
All postsAI & MLAbout VisiumCase studiesDigestTalks & Webinars
JOIN USCONTACT US
Posted on 
May 8, 2020
|
minutes

Turning the Machine Learning Black Box into a Glass Box

Some methods of Machine Learning are referred to as a black box. Take the episode of the Sam Harris podcast featuring an interview with AI pioneer Stuart Russell:

"So, if I’m not mistaken, most, if not all of these deep learning approaches, or even more generally machine learning approaches are essentially black boxes, in which you can’t really inspect how the algorithm is accomplishing what it is accomplishing."

It is indeed difficult to argue against this; however, bear in mind that we choose Machine Learning over traditional statistical methods because Machine Learning tackles larger amounts of data.

The same is true for simple rule-based systems; once the rules are sufficiently complex, understanding the output’s reasoning becomes more difficult. It’s within these complex systems that Machine Learning shines.

We see that the actual black box issue stretches beyond the recent and ubiquitous reference to Machine Learning systems. Nevertheless, as for all complex systems, we need to ensure transparency and explainability.

There are two ways to do so:

1.   Disclosing the single components of a Machine Learning Model: the algorithms and scripts

2.   Explaining why and to what extent various components have influenced an output

At Visium, we ensure both 1) knowledge transfer and 2) explainability of outputs. Turning the black box into a glass box is vital to building trust in AI and Machine Learning.

Do you want to know more about the Pandora's box of Machine Learning? Check out this article written by one of our AI experts. Axel goes into more detail about explainability of outputs and demonstrates how our engineers at Visium achieve this.

https://www.forum-epfl.ch/app/uploads/2019/05/Mag_final.pdf#page=32

‍

Tagged:
ML in Production
Lucas Nottaris
Senior Engagement Manager
view All Posts
Subscribe
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Featured Posts
Digest
Data Cascades, AI for Football, and Protein Generation
Digest
AI in Manufacturing, Google Vertex AI, and Session-Based Recommendations
Digest
Green ML, Interpretable Cancer Detection, and Self-supervised Transformers
Digest
AI Regulations, Car Wreckognition, and External Data Copy
Digest
Melanoma Detection, Bank Customer Confidence and Welding Control
Tags
AI For Good
AI Governance
Document Management
Ethics in AI
Healthcare
Keynotes and Talks
ML in Production
Manufacturing
NLP
Probabilistic Programming
R&D
Retail
Sound AI
Stay Connected
Subscribe

Get new posts to your inbox

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
More Posts

You might also like

AI & ML
AI in Financial Services: 10 questions you should ask before thinking about leveraging new technologies for AML- Fraud detection
Nov 8, 2021
 by 
Digest
Data Cascades, AI for Football, and Protein Generation
Jul 26, 2021
 by 
Digest
AI in Manufacturing, Google Vertex AI, and Session-Based Recommendations
Jun 15, 2021
 by 
AI & ML
Let’s Talk AI Strategy
Jun 4, 2021
 by 
Lucas Nottaris
Digest
Green ML, Interpretable Cancer Detection, and Self-supervised Transformers
Jun 1, 2021
 by 
Digest
AI Regulations, Car Wreckognition, and External Data Copy
May 18, 2021
 by 

We tailor state-of-the-art AI solutions for the world's best brands

Navigation
HomeAboutBlogDigestContactPrivacy policy
Services
AI & data strategyIdeation workshopTailored ML solutionsAI team extensionML operations
© Copyright 2022. All Rights Reserved.
Visium SA