Sign up for our daily briefing
Make your busy days simpler with Axios AM/PM. Catch up on what's new and why it matters in just 5 minutes.
Stay on top of the latest market trends
Subscribe to Axios Markets for the latest market trends and economic insights. Sign up for free.
Sports news worthy of your time
Binge on the stats and stories that drive the sports world with Axios Sports. Sign up for free.
Tech news worthy of your time
Get our smart take on technology from the Valley and D.C. with Axios Login. Sign up for free.
Get the inside stories
Get an insider's guide to the new White House with Axios Sneak Peek. Sign up for free.
Catch up on coronavirus stories and special reports, curated by Mike Allen everyday
Catch up on coronavirus stories and special reports, curated by Mike Allen everyday
Want a daily digest of the top Denver news?
Get a daily digest of the most important stories affecting your hometown with Axios Denver
Want a daily digest of the top Des Moines news?
Get a daily digest of the most important stories affecting your hometown with Axios Des Moines
Want a daily digest of the top Twin Cities news?
Get a daily digest of the most important stories affecting your hometown with Axios Twin Cities
Want a daily digest of the top Tampa Bay news?
Get a daily digest of the most important stories affecting your hometown with Axios Tampa Bay
Want a daily digest of the top Charlotte news?
Get a daily digest of the most important stories affecting your hometown with Axios Charlotte
Illustration: Aïda Amer/Axios
In the quest to build AI that goes beyond today's single-purpose machines, scientists are developing new tools to help AI remember the right things — and forget the rest.
Why it matters: Getting that balance right is the difference between a machine that can trade stocks like a pro but can't make head or tail of a crossword puzzle, and one that learns all that plus a variety of other skills, and continually improves them — an important step toward human-like intelligence.
"AI is entirely about memory and forgetting," says Dileep George, founder of the AI company Vicarious.
- A computer that remembers too little won't be able to do anything that requires connecting past experiences to new ones — like understanding a pronoun in a sentence, even if the person it refers to was named just one sentence before. These memory lapses are known as "catastrophic forgetting."
- But one that remembers too much loses the ability to see the big picture. This is called overfitting: focusing entirely on the particulars of past experiences at the cost of the ability to extract general concepts from them.
- "A big part of learning is knowing what to learn," says David Cox, director of the MIT–IBM Watson AI Lab. "You want to be able to forget things that are irrelevant." This holds for humans and machines both.
Another effect of catastrophic forgetting is that a machine learning a new task can lose the ability to do an old one — like a language learner forgetting their native tongue.
- To solve this, some researchers are adding in memory modules that can set aside learned patterns, so that they don't get overwritten by new information.
- Others, like George, are experimenting with turning specific tasks into computer programs that are walled off from others and can be combined to perform more complex jobs.
These help with AI's forgetting problem — but they're not how human brains work, says Blake Richards, a neuroscientist and AI researcher at the University of Toronto.
- What our brains actually do isn't completely clear, Richards says. It's likely that memories are stored all together — but that patterns are kept separate from each other within the tangle, warding off the overwriting problem.
- Being able to connect memories with one another may be at the root of our ability to imagine and plan — two essential qualities that AI still lacks.
A trick humans do during sleep may be key to moving AI closer to the way we learn, says Cox. At rest, we relive recent memories, and in doing so reinforce neural pathways that help us remember them.
- Machines can mimic this with a process called "experience replay," which weaves in memories of previously learned tasks alongside new lessons.
- This helps them remember the old and the new — and because the memories are not kept separate, a computer could use parts of one to help learn the other, like a typist learning to play piano.
What's next: Perfecting memory could unlock AI "that can actually make insightful predictions and imagine what's going to happen in the future," Richards says. That's a crucial building block toward common sense, long a holy grail for AI researchers.
Go deeper: