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 earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
JUN 11, 2020
Technology
Artificial Brains Need Sleep Too
JUN 11, 2020
Artificial Brains Need Sleep Too
Can your android someday dream of electric sheep? Maybe not. But what may happen is that these artificial brains can ben ...
JUN 23, 2020
Infographics
Frighteningly Fast: 5G by the Numbers
JUN 23, 2020
Frighteningly Fast: 5G by the Numbers
5G is the fifth-generation technology for cellular networks and will likely be the successor to the 4G (fourth-generatio ...
JUL 17, 2020
Technology
How Digital Data Can Determine Your Behavior
JUL 17, 2020
How Digital Data Can Determine Your Behavior
Digital data is the product of our technological uses. Simply opening your smartphone and googling something personal ca ...
SEP 14, 2020
Clinical & Molecular DX
Cell Line Authentication Using STR Analysis
SEP 14, 2020
Cell Line Authentication Using STR Analysis
Imagine you’re studying colon cancer using a colon cell line model. After three painstaking years of research, you ...
OCT 09, 2020
Technology
Deep Learning Advances Drug Design
OCT 09, 2020
Deep Learning Advances Drug Design
Computational data is advancing all areas of medicine and pharmaceutical drug development is certainly no exception. &nb ...
OCT 10, 2020
Drug Discovery & Development
Fishnet of Nanoparticles Traps Drug Molecules
OCT 10, 2020
Fishnet of Nanoparticles Traps Drug Molecules
‘Fishnet’ Nanoparticles Traps Drug Molecules A team at Northwestern University have casted a net of nanopart ...
Loading Comments...