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

Trump whisked out of press briefing after shooting outside White House

President Trump was escorted out of a coronavirus press briefing by a Secret Service agent on Monday after law enforcement reportedly shot an armed suspect outside of the White House.

The state of play: Trump returned to the podium approximately ten minutes later and informed reporters of the news. He said the suspect has been taken to the hospital, but was unable to provide more details and said Secret Service may give a briefing later.

Updated 1 hour ago - Politics & Policy

Coronavirus dashboard

Illustration: Annelise Capossela/Axios

  1. Global: Total confirmed cases as of 5:30 p.m. ET: 19,952,057 — Total deaths: 732,689 — Total recoveries — 12,150,698Map.
  2. U.S.: Total confirmed cases as of 5:30 p.m. ET: 5,074,059 — Total deaths: 163,275 — Total recoveries: 1,656,864 — Total tests: 61,792,571Map.
  3. Politics: House will not hold votes until Sept. 14 unless stimulus deal is reached.
  4. Business: Richer Americans are more comfortable eating out.
  5. Public health: A dual coronavirus and flu threat is set to deliver a winter from hellAt least 48 local public health leaders have quit or been fired during pandemic.
  6. Sports: The cost of kids losing gym class — College football is on the brink.
  7. World: Europe's CDC recommends new restrictions amid "true resurgence in cases."
Updated 2 hours ago - Health

5 states set single-day coronavirus case records last week

Data: Compiled by Axios; Map: Danielle Alberti/Axios

Five states set new highs last week for coronavirus infections recorded in a single day, according to the COVID Tracking Project and state health departments. Only one state — North Dakota — surpassed a record set the previous week.

Why it matters: This is the lowest number of states to see dramatic single-day increases since Axios began tracking weekly highs in June, and marks a continued decrease from late July.