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:
- Halliburton Collaborates With SDAIA to Use Data Science and AI to Enhance Sustainability, Subsurface Predictions in the Energy Sector
Halliburton Company (NYSE: HAL) today announced that it has signed a Memorandum of Understanding (MoU) with the Saudi Data and Artificial Intelligence Authority (SDAIA) to address national and global ...
- How To Leverage AI/ML For Predictive Incident Management
Proactive risk mitigation must be embedded into your enterprise tech strategy to ensure disruption-free operations.
- Automotive Artificial Intelligence Market Report 2022: Rising Industrial Automation to Drive Growth - ResearchAndMarkets.com
The global automotive artificial intelligence market size is projected to grow from USD 2.3 Billion in 2022 to USD 7.0 Billion by 2027, it is expected to grow at a CAGR of 24.1% from 2022 to 2027. The ...
- Putting artificial intelligence and machine learning workloads in the cloud
We look at the pros and cons of putting artificial intelligence (AI) and machine learning (ML) applications in the cloud.
- International students conclude their participation in Global AI Summit to attract global capabilities
A group of AI graduate students in several prestigious international universities concluded their participation in the second edition of the Global Summit on Artificial Intelligence, which concluded ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Deep neural networks
- Even smartest AI models don't match human visual processing: Study
Deep convolutional neural networks (DCNNs) do not see objects the way humans do -- using configural shape perception -- and that could be dangerous in real-world ...
- Deep AI models fail to capture the configural nature of human shape perception
Deep convolutional neural networks (DCNNs) don't see objects the way humans do – using configural shape perception – and that could be dangerous in real-world AI applications, says Professor James ...
- Even smartest AI models don't match human visual processing
Deep convolutional neural networks (DCNNs) don't see objects the way humans do -- using configural shape perception -- and that could be dangerous in real-world AI applications. The study employed ...
- Study highlights how AI models take potentially dangerous 'shortcuts' in solving complex recognition tasks
Deep convolutional neural networks (DCNNs) don't see objects the way humans do—using configural shape perception—and that could be dangerous in real-world AI applications, says Professor James Elder, ...
- AI Capable of Early Detection of Pancreatic Cancer
A new study published in the journal Radiology shows how AI deep learning can detect pancreatic cancer on CT scans with 91 percent accuracy. “The deep learning–based tool enabled accurate detection of ...