Public
- Public
- Network
- Groups
- Featured
- Popular
- People

Hopfield likened searching the network for a saved state to rolling a ball through a landscape of peaks and valleys, with friction that slows its movement. If the ball is dropped in a particular location, it will roll into the nearest valley and stop there. If the network is given a pattern that is close to one of the saved patterns it will, in the same way, keep moving forward until it ends up at the bottom of a valley in the energy landscape, thus finding the closest pattern in its memory.

Download link

Hopfield likened searching the network for a saved state to rolling a ball through a landscape of peaks and valleys, with friction that slows its movement. If the ball is dropped in a particular location, it will roll into the nearest valley and stop there. If the network is given a pattern that is close to one of the saved patterns it will, in the same way, keep moving forward until it ends up at the bottom of a valley in the energy landscape, thus finding the closest pattern in its memory.
https://files.mastodon.social/media_attachments/files/113/271/705/972/627/888/original/6c169b8080cf720d.webp

Notices where this attachment appears

Embed this notice
Corey S Powell (coreyspowell@mastodon.social)'s status on Tuesday, 08-Oct-2024 21:28:18 JST Corey S Powell

The Nobel Prize in Physics goes to John Hopfield & Geoffrey Hinton for work in machine learning and neural networks.
Here's why that research qualifies as physics (it's also a fascinating read):
https://www.nobelprize.org/prizes/physics/2024/popular-information/ #science #physics #nobel #tech

In conversation about 2 months ago from mastodon.social permalink