Grasping Concept Spaces: Revision history

From Computer Laboratory Group Design Projects
Jump to navigationJump to search

Diff selection: Mark the radio buttons of the revisions to compare and hit enter or the button at the bottom.
Legend: (cur) = difference with latest revision, (prev) = difference with preceding revision, m = minor edit.

29 October 2024

28 October 2024

  • curprev 16:1116:11, 28 October 2024afb21 talk contribs 549 bytes +549 Created page with "Client: Sam Henshall-West, JAID <sam.henshall-west@jaid.io> Today's most powerful machine learning models, including generative AI LLMs like ChatGPT, encode their knowledge as higher dimensional latent spaces. Vector-based concepts in that space can be clustered as regions on a 2D screen, for example using the t-SNE visualisation algorithm. Your task is to create a 3D version of t-SNE that is interactive, so users with VR headsets can literally “grasp” a concept, an..."