Skip to main content
Artificial Intelligence

Return to Question

added 101 characters in body
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 114
  • 205

I learned from this blog post Self-Supervised Learning: The Dark Matter of Intelligence that

enter image description here

We believe that self-supervised learning (SSL) is one of the most promising ways to build such background knowledge and approximate a form of common sense in AI systems.

I wonder whatWhat are other most promising ways which would be competitive to self-supervised learning?

I only know the knowledge baseknowledge base, but I don't think it would be that promising due to the curation problem of the large scale Automated Knowledge Base Construction.

I learned from this blog post Self-Supervised Learning: The Dark Matter of Intelligence that

enter image description here

I wonder what are other most promising ways which would be competitive to self-supervised learning?

I only know the knowledge base, but I don't think it would be that promising due to the curation problem of the large scale Automated Knowledge Base Construction.

I learned from this blog post Self-Supervised Learning: The Dark Matter of Intelligence that

We believe that self-supervised learning (SSL) is one of the most promising ways to build such background knowledge and approximate a form of common sense in AI systems.

What are other most promising ways which would be competitive to self-supervised learning?

I only know the knowledge base, but I don't think it would be that promising due to the curation problem of the large scale Automated Knowledge Base Construction.

Source Link
Lerner Zhang
Lerner Zhang
  • 967
  • 1
  • 7
  • 21

What are some most promising ways to approximate common sense and background knowledge?

I learned from this blog post Self-Supervised Learning: The Dark Matter of Intelligence that

enter image description here

I wonder what are other most promising ways which would be competitive to self-supervised learning?

I only know the knowledge base, but I don't think it would be that promising due to the curation problem of the large scale Automated Knowledge Base Construction.