We don’t always know why ‘intelligent’ machines do what they do. Should we study them like animals?

bsip dpi
Image: Amelie-Benoist/BSIP

Artificial intelligence algorithms are often seen as ‘black boxes’ whose rules remain inaccessible. We must therefore create a new scientific discipline to understand the behaviour of the machines that rely on them, as we did for the study of animal behaviour. This is the perspective of Jean-François Bonnefon, who along with 22 other scientists just signed an editorial in the journal Nature.

Understanding the behaviour of intelligent machines is a broader objective than understanding how they are programmed. Sometimes a machine’s programming is not accessible, for example when its code is a trade secret. In this case, it is important to understand a machine from the outside, by observing its actions and measuring their consequences. Other times, it is not possible to completely predict a machine’s behaviour based on its code, because this behaviour will change in a complex manner when the machine adapts to its environment through a learning process, guided but ultimately opaque. In this case, we need to continually observe this behaviour, and simulate its potential evolution.

Related article:  Artificial intelligence could predict where earthquake aftershocks will strike

ADVERTISEMENT

A new scientific discipline dedicated to machine behaviour is needed to meet these challenges, just as we created the scientific discipline of animal behaviour.

Read full, original post: Is a Robot just another “Animal”?

Outbreak Daily Digest
Biotech Facts & Fallacies
GLP Podcasts
Infographic: Here’s where GM crops are grown around the world today

Infographic: Here’s where GM crops are grown around the world today

Do you know where biotech crops are grown in the world? This updated ISAAA infographics show where biotech crops were ...
News on human & agricultural genetics and biotechnology delivered to your inbox.
glp menu logo outlined

Newsletter Subscription

* indicates required
Email Lists
Send this to a friend