Memory abilities to make neural networks less forgetful

Memory abilities to make neural networks less 'forgetful'

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 be able to tell cats from foxes without having ever seen a cat and a fox at the same time,” 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.”

Subscribe to our newsletter

Related articles

Neural networks: artificial brains need sleep too

Neural networks: artificial brains need sleep too

States that resemble sleep-like cycles in simulated neural networks quell the instability that comes with uninterrupted self-learning in artificial analogs of brains.

A computer reads and predicts thoughts

A computer reads and predicts thoughts

Researchers at the University of Helsinki have developed a technique in which a computer models visual perception by monitoring human brain signals.

Optimizing neural networks on a brain-inspired computer

Optimizing neural networks on a brain-inspired computer

Research shows how so-called “critical states” can be used to optimize artificial neural networks running on brain-inspired neuromorphic hardware.

AI used to identify different types of brain injuries

AI used to identify different types of brain injuries

Researchers have developed an AI algorithm that can detect and identify different types of brain injuries.

Neural networks help cardiac diagnostics

Neural networks help cardiac diagnostics

Artificial intelligence may be an aid to interpreting ECG results, helping healthcare staff to diagnose diseases that affect the heart.

AI model accurately classifies colorectal polyps

AI model accurately classifies colorectal polyps

An AI model for automated classification of colorectal polyps could benefit cancer screening programs by improving efficiency, reproducibility, and accuracy.

AI challenge aims to improve mammography accuracy

AI challenge aims to improve mammography accuracy

AI techniques, used in combination with the evaluation of expert radiologists, improve the accuracy in detecting cancer using mammograms.

AI and laser-based imaging system identify brain tumors

AI and laser-based imaging system identify brain tumors

A novel method of combining advanced optical imaging with an artificial intelligence algorithm produces accurate, real-time intraoperative diagnosis of brain tumors.

Using AI to reveal how memories are coded in the brain

Using AI to reveal how memories are coded in the brain

Researchers have discovered that a population of neurons in the brain’s frontal lobe contain stable short-term memory information within dynamically-changing neural activity.

Popular articles