News for hackers. Stuff that matters.
Re:Google’s AI Wizard Unveils a New Twist on Neural Networks by adventured on Wednesday November 08, 2017 @09:57AM (#15652987)
You remember the semantic web and what it was supposed to accomplish (...describing and linking every entity possible to create a new concept of understanding and knowledge utilization in the digital space)? It was all the rage ~8 years ago and mostly flopped.

Capsules are kind of like that effort, for the current AI push. They're meant to make it possible to understand smaller entities and how they pertain to a larger more complex entity. The smaller entities can inform as to the identity of the larger entity (particularly in combination, and increase or decrease accuracy depending on the combination), without having to have a perfect or clear picture of that larger entity.

In the semantic web, a complex entity might be cross-linked to a dozen or several dozen smaller entities that help describe the larger entity. With enough of the smaller entities (attributes of the larger entity) you could map and narrow down what the larger entity possibilities are.

Re:Google’s AI Wizard Unveils a New Twist on Neural Networks by randcraw on Wednesday November 08, 2017 @11:06AM (#15653752)
As I understand it, Hinton has also referred to capsules as "thought vectors". (I think) a capsule is an encoding of information in a persistent mobile form that allows it to be reused in other contexts / nets / knowledgebases -- like a word2vec word definition vector which contains the scores of the most informative n (principal) component words for the given word.

Another obvious attraction of capsules would be the potential to recognize, tune, and maybe even manually introduce labeled concepts in nets during training -- perhaps enabling one shot learning?

Re:Google’s AI Wizard Unveils a New Twist on Neural Networks by p1esk on Wednesday November 08, 2017 @12:27PM (#15654573)
Another obvious attraction of capsules would be the potential to recognize, tune, and maybe even manually introduce labeled concepts in nets during training -- perhaps enabling one shot learning?

This is not obvious to me at all. Can you please explain?