Skip to Content

An App so You’ll Never Forget

Adaptive-learning algorithms calculate how often people need to see information to remember it.
November 3, 2009

A language-learning application that’s already big in Japan is coming to the U.S. in the form of a new iPhone app. Smart.fm, based in Tokyo, says that the adaptive-learning algorithms behind its software can help users memorize all kinds of information.

Remember this: Though originally designed for language learning, Smart.fm’s software has been expanded; now the system can include user-generated material on topics such as the Internet memes shown above.

Smart.fm is one of several companies selling software designed to help users remember. The company’s algorithms were inspired by research that shows people remember information more effectively they try to memorize it at key times, says founder and chairman Andrew Smith Lewis.

Those algorithms determine how often to present a piece of information to the user and in what context. For example, a completely new word and its translation are shown frequently, and a user is asked relatively easy questions about them, designed to jog the memory. But once the user has demonstrated the ability to recall that word and its meaning, this information will appear less often.

“Efficiency is the main thing,” Lewis says. “We want to optimize the sweet spot between the minimum number of times you have to see an item and the maximum effectiveness of that presentation.”

To use Smart.fm, a person selects an existing list of material–a dictionary of foreign words, for instance–or starts building a new list. The list could be text-only, but the system also supports images and audio. A user might match the names of birds to the sounds they make, or view images of different parts of the human brain in order to learn how to identify them. Someone who snaps pictures of the people she meets at a conference might use the software to commit those people’s names to memory.

“Learning applications which present stimuli adaptively based on the forgetting curve are not new but still relatively rare,” says Peter Brusilovsky, director of the Personalized Adaptive Web Systems Lab at the University of Pittsburgh’s School of Information Sciences. But Smart.fm’s teaching methods can be applied to any type of material, Lewis says. “The adaptive-learning platform doesn’t know if you’re studying Russian painters or chess moves or French verbs,” he says. “It just knows that these are individual objects.”

Unlike other memory applications, Smart.fm takes a social approach, letting users share their lists and add comments to other lists. And in the future, Lewis says, there will be more ways to pull information into the system. The company is working on integrating with Freebase, a site that collects user-generated databases. Once the effort is complete, Smart.fm users who are interested in a particular topic should be able to access information about it from Freebase automatically.

“Education apps are one of the most interesting and growing areas of the iPhone app store,” says Carl Howe, an analyst focusing on mobile research at the Yankee Group. Howe thinks Smart.fm was wise to broaden the scope of its material beyond just language learning. For education apps, he says, “the central aspect is knowing how to engage people’s interest.”

Howe notes that the top education apps for the iPhone are geared toward middle-school and elementary-school children. He believes there’s a huge opportunity for college-level material, too. But companies designing e-learning apps may find themselves competing with material from established universities such as MIT and Stanford, which offer free material for self-directed study online.

Smart.fm’s business model is based largely on the prospect of collaboration with other companies and institutions that want to offer online learning. The company has already partnered with the Japanese telecom giant NTT, which has used the software to create learning sites focusing on specific topics.

Lewis hopes that such deals will become Smart.fm’s main source of revenue, though he also suggests that Smart.fm may offer premium content to users for a price. The iPhone app, however, is and will remain free.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.