Post Thumb

AI helps computers hone the fine art of forgetting

Share it

Deep learning is changing the way we use and think about machines. These guys have shown that the approach biological systems use to learn, and to forget, can work with artificial neural networks too.

The key is a process known as Hebbian learning, first proposed in the 1940s by the Canadian psychologist Donald Hebb to explain the way brains learn via synaptic plasticity.

So Aljundi and co have developed a way for artificial neural networks to behave in the same way. Neural networks with memory aware synapses turn out to perform better in these tests than other networks. The key point is that the team has found a way for neural networks to employ Hebbian learning.

If these scientists can make their version of Hebbian learning better, it should make machines more flexible in their learning.


Article originally posted at

Post Author: John Koetsier

1 thought on “AI helps computers hone the fine art of forgetting

    Richard Saunders

    (January 23, 2018 - 8:17 pm)

    The most limited resource is not storage capacity but time–the time it takes to retrieve and rank the most relevant memories.

Leave a Reply

Your email address will not be published. Required fields are marked *