Uncommon Descent Serving The Intelligent Design Community

Missing data hinder replication in AI studies too?

Share
Facebook
Twitter
LinkedIn
Flipboard
Print
Email
controls for AI/Pbroks13

From Matthew Hutson at Science:

The booming field of artificial intelligence (AI) is grappling with a replication crisis, much like the ones that have afflicted psychology, medicine, and other fields over the past decade. AI researchers have found it difficult to reproduce many key results, and that is leading to a new conscientiousness about research methods and publication protocols. “I think people outside the field might assume that because we have code, reproducibility is kind of guaranteed,” says Nicolas Rougier, a computational neuroscientist at France’s National Institute for Research in Computer Science and Automation in Bordeaux. “Far from it.” Last week, at a meeting of the Association for the Advancement of Artificial Intelligence (AAAI) in New Orleans, Louisiana, reproducibility was on the agenda, with some teams diagnosing the problem—and one laying out tools to mitigate it.

Assuming you can get and run the original code, it still might not do what you expect. In the area of AI called machine learning, in which computers derive expertise from experience, the training data for an algorithm can influence its performance. Ke suspects that not knowing the training for the speech-recognition benchmark was what tripped up her group. “There’s randomness from one run to another,” she says. You can get “really, really lucky and have one run with a really good number,” she adds. “That’s usually what people report.” More.

Gambling addicts complain about that all the time.

See also: Robert Marks on the Turing Test vs the Lovelace Test for computer intelligence

At Technology Review: There is no clear path to giving computers the power to think

and

At Nautilus: Scientists should not accept unreplicated results (Yawn.)

Comments
There isn't randomness, there's quality of data. In these systems, the data is also the code. It's just a procedural parameterization. Looks like they've been sloppy and not bothering to record the input well enough. Hard to adjust your adaptive algorithm if you didn't even bother to keep track of what you've been feeding it.LocalMinimum
February 17, 2018
February
02
Feb
17
17
2018
04:30 PM
4
04
30
PM
PDT

Leave a Reply