Nav: Home

Framework improves 'continual learning' for artificial intelligence

May 15, 2019

Researchers have developed a new framework for deep neural networks that allows artificial intelligence (AI) systems to better learn new tasks while "forgetting" less of what it has learned regarding previous tasks. The researchers have also demonstrated that using the framework to learn a new task can make the AI better at performing previous tasks, a phenomenon called backward transfer.

"People are capable of continual learning; we learn new tasks all the time, without forgetting what we already know," says Tianfu Wu, an assistant professor of electrical and computer engineering at NC State and co-author of a paper on the work. "To date, AI systems using deep neural networks have not been very good at this."

"Deep neural network AI systems are designed for learning narrow tasks," says Xilai Li, a co-lead author of the paper and a Ph.D. candidate at NC State. "As a result, one of several things can happen when learning new tasks. Systems can forget old tasks when learning new ones, which is called catastrophic forgetting. Systems can forget some of the things they knew about old tasks, while not learning to do new ones as well. Or systems can fix old tasks in place while adding new tasks - which limits improvement and quickly leads to an AI system that is too large to operate efficiently. Continual learning, also called lifelong-learning or learning-to-learn, is trying to address the issue."

"We have proposed a new framework for continual learning, which decouples network structure learning and model parameter learning," says Yingbo Zhou, co-lead author of the paper and a research scientist at Salesforce Research. "We call it the Learn to Grow framework. In experimental testing, we've found that it outperforms previous approaches to continual learning."

To understand the Learn to Grow framework, think of deep neural networks as a pipe filled with multiple layers. Raw data goes into the top of the pipe, and task outputs come out the bottom. Every "layer" in the pipe is a computation that manipulates the data in order to help the network accomplish its task, such as identifying objects in a digital image. There are multiple ways of arranging the layers in the pipe, which correspond to different "architectures" of the network.

When asking a deep neural network to learn a new task, the Learn to Grow framework begins by conducting something called an explicit neural architecture optimization via search. What this means is that as the network comes to each layer in its system, it can decide to do one of four things: skip the layer; use the layer in the same way that previous tasks used it; attach a lightweight adapter to the layer, which modifies it slightly; or create an entirely new layer.

This architecture optimization effectively lays out the best topology, or series of layers, needed to accomplish the new task. Once this is complete, the network uses the new topology to train itself on how to accomplish the task - just like any other deep learning AI system.

"We've run experiments using several datasets, and what we've found is that the more similar a new task is to previous tasks, the more overlap there is in terms of the existing layers that are kept to perform the new task," Li says. "What is more interesting is that, with the optimized - or "learned" topology - a network trained to perform new tasks forgets very little of what it needed to perform the older tasks, even if the older tasks were not similar."

The researchers also ran experiments comparing the Learn to Grow framework's ability to learn new tasks to several other continual learning methods, and found that the Learn to Grow framework had better accuracy when completing new tasks.

To test how much each network may have forgotten when learning the new task, the researchers then tested each system's accuracy at performing the older tasks - and the Learn to Grow framework again outperformed the other networks.

"In some cases, the Learn to Grow framework actually got better at performing the old tasks," says Caiming Xiong, the research director of Salesforce Research and a co-author of the work. "This is called backward transfer, and occurs when you find that learning a new task makes you better at an old task. We see this in people all the time; not so much with AI."
-end-
The paper, "Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting," will be presented at the 36th International Conference on Machine Learning, being held June 9-15 in Long Beach, California. Co-lead authors of the paper are Xilai Li, a Ph.D. student at NC State, and Yingbo Zhou of Salesforce Research. The paper was co-authored by Richard Socher and Caiming Xiong of Salesforce Research.

The work was done with support from the U.S. Army Research Office under grants W911NF1810295 and W911NF1810209; and from the National Science Foundation, under grant 1822477. Part of the work was done while Li was a summer intern at Salesforce AI Research.

North Carolina State University

Related Learning Articles:

School spending cuts triggered by great recession linked to sizable learning losses for learning losses for students in hardest hit areas
Substantial school spending cuts triggered by the Great Recession were associated with sizable losses in academic achievement for students living in counties most affected by the economic downturn, according to a new study published today in AERA Open, a peer-reviewed journal of the American Educational Research Association.
Lessons in learning
A new Harvard study shows that, though students felt like they learned more from traditional lectures, they actually learned more when taking part in active learning classrooms.
Learning to look
A team led by JGI scientists has overhauled the perception of inovirus diversity.
Sleep readies synapses for learning
Synapses in the hippocampus are larger and stronger after sleep deprivation, according to new research in mice published in JNeurosci.
Learning from experience is all in the timing
Animals learn the hard way which sights, sounds, and smells are relevant to survival.
More Learning News and Learning Current Events

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Erasing The Stigma
Many of us either cope with mental illness or know someone who does. But we still have a hard time talking about it. This hour, TED speakers explore ways to push past — and even erase — the stigma. Guests include musician and comedian Jordan Raskopoulos, neuroscientist and psychiatrist Thomas Insel, psychiatrist Dixon Chibanda, anxiety and depression researcher Olivia Remes, and entrepreneur Sangu Delle.
Now Playing: Science for the People

#537 Science Journalism, Hold the Hype
Everyone's seen a piece of science getting over-exaggerated in the media. Most people would be quick to blame journalists and big media for getting in wrong. In many cases, you'd be right. But there's other sources of hype in science journalism. and one of them can be found in the humble, and little-known press release. We're talking with Chris Chambers about doing science about science journalism, and where the hype creeps in. Related links: The association between exaggeration in health related science news and academic press releases: retrospective observational study Claims of causality in health news: a randomised trial This...