Toot

Written by ma𝕏pool on 2024-12-19 at 13:21

The Dimensions of dimensionality

https://www.cell.com/trends/cognitive-sciences/fulltext/S1364-6613(24)00189-X#

Globally interpretable feature dimensions are one property, among others like prediction performance and compactness, that researchers can prioritize when inferring latent representations.

Multidimensional representational spaces can capture complex structures such as hierarchical relationships, lexical entailment, and compositional features.

Superficially different representations, such as graphs and multidimensional data, can capture the same structural relationships under appropriate settings.

The dimensionality of a representation conveys relatively little information on its own.

[#]representation #dimensionality #cogsci #ml #datascience

=> View attached media | View attached media

=> More informations about this toot | View the thread | More toots from maxpool@mathstodon.xyz

Mentions

Tags

=> View datascience tag | View ml tag | View cogsci tag | View dimensionality tag | View representation tag

Proxy Information
Original URL
gemini://mastogem.picasoft.net/toot/113679694343399108
Status Code
Success (20)
Meta
text/gemini
Capsule Response Time
225.128023 milliseconds
Gemini-to-HTML Time
0.572957 milliseconds

This content has been proxied by September (3851b).