Hidden Layer Interaction: A Co-Creative Design Fiction for Generative Models

Research output: Contribution to conference - NOT published in proceeding or journalPaperResearchpeer-review

Abstract

This paper presents a speculation on a fictive co-creation scenario that extends classical interaction patterns with generative models. While existing interfaces are restricted to the input and output layers, we suggest hidden layer interaction to extend the horizonal relation at play when co-creating with a generative model’s design space. We speculate on applying feature visualization to ma- nipulate neurons corresponding to features ranging from edges over textures to objects. By integrating visual representations of a neural network’s hidden layers into co-creation, we aim to provide humans with a new means of interaction, contributing to a phenomenological account of the model’s inner workings during generation.
Original languageEnglish
Publication dateApr 2023
DOIs
Publication statusPublished - Apr 2023
EventCHI '23 -
Duration: 23 Apr 2023 → …

Conference

ConferenceCHI '23
Period23/04/2023 → …

Fingerprint

Dive into the research topics of 'Hidden Layer Interaction: A Co-Creative Design Fiction for Generative Models'. Together they form a unique fingerprint.

Cite this