SEP 17, 2020 6:29 PM PDT

Advancing Memory in AI Neural Networks

WRITTEN BY: Nouran Amin

Improving The Memory of Neural Networks via Artificial intelligence (AI)

Using the human brain as inspiration, researchers at the University of Massachusetts Amherst and the Baylor College of Medicine have reported a way in improving neural network memory.

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."

Naturally, humans are able to collect information and build on it through experiences. One way our brains remember old information is through a critical mechanism involving the ‘replay’ of neuronal activity.  This mechanism is not found in AI neuronal networks. Findings were published in Nature Communications.

Learn more about neural networks:

Hava Siegelmann at UMass Amherst notes, "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."

"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,” explains first author and postdoctoral researcher Gido van de Ven. “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."

Findings were published in Nature Communications.

Source: Science Daily

About the Author
  • Nouran is a scientist, educator, and life-long learner with a passion for making science more communicable. When not busy in the lab isolating blood macrophages, she enjoys writing on various STEM topics.
You May Also Like
NOV 27, 2020
Clinical & Molecular DX
From Months to Hours - Digital Tools Accelerate Dermatological Diagnoses
NOV 27, 2020
From Months to Hours - Digital Tools Accelerate Dermatological Diagnoses
Getting that nasty rash tested isn’t always a straightforward process. Dermatologists have notoriously long waitli ...
FEB 01, 2021
Technology
Computer Science and The Brain
FEB 01, 2021
Computer Science and The Brain
The world is seeing an increase in students interested in computer science and the age of students beginning to code is ...
FEB 17, 2021
Technology
Emojis and The Negative Vibe
FEB 17, 2021
Emojis and The Negative Vibe
Research has found that typing those negative emojis in your texts can make you appear negative to the sender. The study ...
FEB 22, 2021
Technology
Smartphones Can Measure Food Consumption
FEB 22, 2021
Smartphones Can Measure Food Consumption
Scientists have devised a new method of using smartphones to measure food consumption and to predict physical well-being ...
FEB 25, 2021
Technology
New Development for Electrochromatic Devices
FEB 25, 2021
New Development for Electrochromatic Devices
Scientists have developed a new approach for foldable and solid devices—best known as solid and flexible electroch ...
MAR 15, 2021
Technology
Computational Methods for Water
MAR 15, 2021
Computational Methods for Water
Water is essential and may as well be Earth's most critical natural resource. As such, scientists are looking for wa ...
Loading Comments...