Affiliation:
1. Architecture, Columbia University, Somerville, MA, USA
Abstract
This paper recommends that critical attention towards machine learning should be focused on the ordering procedures at work in these models. More precisely, it draws attention to the central role of ‘latent spaces.’ The paper first explores ‘latent space’ through a series of analogies, and then briefly situates the concept in relation to a genealogy reaching back to developments in mathematical statistics at the turn to the 20th century.
Subject
Computer Graphics and Computer-Aided Design,Computer Science Applications,Building and Construction