via Baylor College of Medicine
UMass Amherst, Baylor researchers collaborate on imitating brain’s ‘replay’ ability
Artificial intelligence (AI) experts at the University of Massachusetts Amherst and the Baylor College of Medicine report that they have successfully addressed what they call a “major, long-standing obstacle to increasing AI capabilities” by drawing inspiration from a human brain memory mechanism known as “replay.”
First author and postdoctoral researcher Gido van de Ven and principal investigator Andreas Tolias at Baylor, with Hava Siegelmann at UMass Amherst, write in Nature Communications that they have developed a new method to protect – “surprisingly efficiently” – deep neural networks from “catastrophic forgetting” – upon learning new lessons, the networks forget what they had learned before.
Siegelmann and colleagues point out that deep neural networks are the main drivers behind recent AI advances, but progress is held back by this forgetting.
They write, “One solution would be to store previously encountered examples and revisit them when learning something new. Although such ‘replay’ or ‘rehearsal’ solves catastrophic forgetting,” they add, “constantly retraining on all previously learned tasks is highly inefficient and the amount of data that would have to be stored becomes unmanageable quickly.”
Unlike AI neural networks, humans are able to continuously accumulate information throughout their life, building on earlier lessons. An important mechanism in the brain believed to protect memories against forgetting is the replay of neuronal activity patterns representing those memories, they explain.
Siegelmann says the team’s major insight is in “recognizing that replay in the brain does not store data.” Rather, “the brain generates representations of memories at a high, more abstract level with no need to generate detailed memories.” Inspired by this, she and colleagues created an artificial brain-like replay, in which no data is stored. Instead, like the brain, the network generates high-level representations of what it has seen before.
The “abstract generative brain replay” proved extremely efficient, and the team showed that replaying just a few generated representations is sufficient to remember older memories while learning new ones. Generative replay not only prevents catastrophic forgetting and provides a new, more streamlined path for system learning, it allows the system to generalize learning from one situation to another, they state.
For example, “if our network with generative replay first learns to separate cats from dogs, and then to separate bears from foxes, it will also tell cats from foxes without specifically being trained to do so. And notably, the more the system learns, the better it becomes at learning new tasks,” says van de Ven.
He and colleagues write, “We propose a new, brain-inspired variant of replay in which internal or hidden representations are replayed that are generated by the network’s own, context-modulated feedback connections. Our method achieves state-of-the-art performance on challenging continual learning benchmarks without storing data, and it provides a novel model for abstract level replay in the brain.”
Van de Ven says, “Our method makes several interesting predictions about the way replay might contribute to memory consolidation in the brain. We are already running an experiment to test some of these predictions.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Bringing the power of industrial artificial intelligence to the chemical industryon November 29, 2020 at 6:01 am
Incorporating AI into existing operating technology (OT) and information technology (IT) enables easier adoption, and when combined with domain expertise in the chemical industry, brings new levels of ...
- Ethical AI isn’t the same as trustworthy AI, and that matterson November 28, 2020 at 6:25 pm
Certainly, unethical systems create mistrust. It does not follow, however, that an ethical system will be categorically trusted.
- Emily Murphy, Administrator Of The GSA Shares Her Thoughts On AIon November 28, 2020 at 6:28 am
Being recently thrust into the news, Emily Murphy, Administrator of the GSA might have rather been known for the impact she has helped make on the GSA's use of AI and automation to change the way the ...
- MQ-9 to be Enhanced with AI Capabilitieson November 28, 2020 at 2:00 am
Artificial intelligence (AI) dramatically enhances the capabilities of autonomous systems. The US Joint Artificial Intelligence ...
- Cloud and AI: The biggest trends in personal and SMB video surveillanceon November 27, 2020 at 3:50 pm
Video surveillance systems are increasing in power and value, as new ways to gather, analyze, share, and store digital data are developed.
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Deep neural networks
- How archaeologists are using deep learning to dig deeperon November 26, 2020 at 3:04 am
Finding the tomb of an ancient king full of golden artifacts, weapons and elaborate clothing seems like any archaeologist’s fantasy. But searching for them, Gino Caspari can tell you, is incredibly ...
- Binarized neural networks show promise for fast, accurate machine learningon November 24, 2020 at 5:14 am
As anyone with a green thumb knows, pruning can promote thriving vegetation. A snip here, a snip there, and growth can be controlled and directed for a more vigorous plant.
- Internet of Things and deep learning: How your devices are getting smarteron November 24, 2020 at 3:40 am
The latest neural network from Massachusetts Institute of Technology shows a great bound forward for deep learning and the ...
- Researchers bring deep learning to IoT deviceson November 23, 2020 at 8:08 pm
MIT researchers have developed a system that could bring deep learning neural networks to a variety of objects that constitute the IoT.
- MIT neural network knows when it can be trustedon November 23, 2020 at 4:47 am
Deep learning neural networks are artificial intelligence systems that are being used for increasingly important decisions. Deep learning neural networks are used for tasks as varied as autonomous ...