Wednesday, June 28, 2017

The unintelligibility/opacity of AI systems

In the old days of classical symbolic AI program logic was "hand-coded" and based on expert knowledge of the application domain. It was thus possible, at least in principle, to figure out why the program did what it did in any particular case. That's not true of contemporary AI systems that use so-called "deep learning", which more or less program themselves. Writing about a self-driving car, Will Knight observes:
Getting a car to drive this way was an impressive feat. But it’s also a bit unsettling, since it isn’t completely clear how the car makes its decisions. Information from the vehicle’s sensors goes straight into a huge network of artificial neurons that process the data and then deliver the commands required to operate the steering wheel, the brakes, and other systems. The result seems to match the responses you’d expect from a human driver. But what if one day it did something unexpected—crashed into a tree, or sat at a green light? As things stand now, it might be difficult to find out why. The system is so complicated that even the engineers who designed it may struggle to isolate the reason for any single action. And you can’t ask it: there is no obvious way to design such a system so that it could always explain why it did what it did.
Of course, this has legal implications:
There’s already an argument that being able to interrogate an AI system about how it reached its conclusions is a fundamental legal right. Starting in the summer of 2018, the European Union may require that companies be able to give users an explanation for decisions that automated systems reach. This might be impossible, even for systems that seem relatively simple on the surface, such as the apps and websites that use deep learning to serve ads or recommend songs. The computers that run those services have programmed themselves, and they have done it in ways we cannot understand. Even the engineers who build these apps cannot fully explain their behavior.

No comments:

Post a Comment