Updated May 10, 2018

Why good AI should be able to show its work

Illustration: Lazaro Gamio/Axios

The first step to ethical artificial intelligence is teaching the computer to explain its decision making, something known in the field as explainable AI.

Why it matters: Right now many deep learning algorithms don't make it clear how they arrived at their predictions or conclusions. That lack of visibility into the data, steps and calculations that went into an outcome makes it hard to root out bias or other algorithmic errors that could impact results like who gets a loan or how much a factory should produce.

What's happening: Explainable AI, also sometimes called transparent AI, has become a top priority for nearly all the big companies in the AI field, including Microsoft, Google, Intel, IBM and Oracle. The topic is also expected to come up in Thursday's White House meeting on AI.

  • IBM's guidelines put it pretty simply: "Companies must be able to explain what went into their algorithm’s recommendations. If they can’t, then their systems shouldn’t be on the market."

That sounds straightforward, even obvious. But it actually isn't a feature built into many of the deep learning systems that are currently available.

No one size fits all: AI was a huge topic at Google's I/O developer conference this week, with some focus on explainability as well.

  • One very basic example is the new personalized scores in Google Maps for locations. In that case, Google's AI can also say why it thought that restaurant is a good fit by showing a few of the factors that led to the recommendation.
  • By contrast, doctors wanting to know why an AI system made a clinical diagnosis are going to want a far more detailed explanation.
  • "The kind of information you need in different scenarios really is fundamentally different," Google principal scientist Greg Corrado told Axios. "It's not possible to have one uniform standard for what constitutes explainability."

How it works: There are different ways for an AI system to explain itself.

  • One is to be able to show which variables led to different decisions and how heavily each was weighted. In the Google restaurant example, the program might explain its recommendation by noting a user tends to greatly prefer restaurants that are kid-friendly and often goes to pizza places.
  • In other instances, it could be enough to offer people the ability to adjust different pieces of data to see if that changes the conclusion.

What is explainable enough? Microsoft Research director Eric Horvitz likens the problem to getting a car fixed. You don't have to know exactly how the carburetor on a car works, as long as your mechanic does. That opens up the question of just how explainable AI needs to be for specific users and specific purposes.

"I think we need to do more research on what is a satisfying answer to a human being," he said.

It's not just Big Tech: DARPA, the Defense Department's advanced research arm, has a program on Explainable AI. The stakes are obviously huge when AI is helping guide decisions of who to attack, how and when.

"The DoD has to have, I would argue, a much higher bar ," DARPA's Brian Pierce told Axios.

Government's role: IBM hopes to raise the topic at today's White House AI summit.

“If the government’s going to do anything in terms of encouraging or even potentially regulating AI, the main focus has got to be on this issue of explainability," said Chris Padilla, who leads IBM's government affairs efforts.

What else: Explainability is a necessary ingredient for ethical AI, but it's really just a start. Other keys are eliminating bias, both in the data used to "train" the programs and in the algorithms themselves.

  • There is a separate question concerning what tasks should be reserved only for humans.
  • Many believe, for example, that allowing AI-powered autonomous weapons systems is a bad idea.

Go deeper: Here are several more looks at the need for (and means of creating) explainable AI.

Go deeper

Public transit's death spiral

Illustration: Eniola Odetunde/Axios

Public transit systems across the country are experiencing a painful trifecta: Ridership has collapsed, funding streams are squeezed, and mass transit won't bounce back from the pandemic nearly as fast as other modes of transportation.

Why it matters: Transit agencies could see an annual shortfall of as much as $38 billion due to the coronavirus pandemic, according to TransitCenter. At the same time, they're more important than ever, with more than 36% of essential workers relying on public transportation to get to work.

Go deeperArrow15 mins ago - Health

World coronavirus updates: London mayor says U.K. nowhere near lockdown lifting

Data: The Center for Systems Science and Engineering at Johns Hopkins; Map: Andrew Witherspoon/Axios

Prime Minister Jacinda Ardern offered hope in the fight against the novel coronavirus, saying she believes New Zealand has "turned a corner" after two weeks of strict lockdown measures. But London Mayor Sadiq Khan has said the U.K. is "nowhere near" lifting restrictions.

The big picture: COVID-19 has killed over 82,000 people and infected 1.4 million others globally as of early Wednesday, per Johns Hopkins data. Global recoveries have surpassed 301,000. Spain has reported the most cases outside the U.S. (more than 141,000) and Italy the most deaths (over 17,000). Half the planet's population is on lockdown.

Go deeperArrowUpdated 39 mins ago - Health

Wisconsin may be the start of the 2020 election wars

Illustration: Aïda Amer/Axios

Wisconsin voters braving lines in face masks — after a last-minute Supreme Court ruling against extending the absentee deadline — could foreshadow a nationwide legal struggle over how to conduct elections during the coronavirus outbreak, election experts say.

Why it matters: "It's a harbinger of what's to come in the next skirmishes in the voting wars" from now through November, Richard Hasen, a professor and national election law expert at the University of California, Irvine, told Axios.