Perceptions
Perceptions
Perceptions is a study of how a machine perceives a photograph at different layers within its neural network. We generate sets of pen strokes which are drawn by a robot using pen and ink on Bristol board. The illustrations are produced by maximising the similarity between the machine's internal perception of the illustration and chosen target photographs. The study focusses on the difference between different inductive biases (shape versus texture) in the training of the neural network, as well as how the machine's perception changes as a function of depth within its network. The photos chosen are from travels to far away cities, taken before the COVID-19 pandemic.
Mihai, Daniela
f8910fe1-18e7-45b3-8923-b34b5cd136fa
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
13 December 2021
Mihai, Daniela
f8910fe1-18e7-45b3-8923-b34b5cd136fa
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Mihai, Daniela and Hare, Jonathon
(2021)
Perceptions.
The AI Art Gallery: NeurIPS Workshop on Machine Learning for Creativity and Design 2021.
Record type:
Art Design Item
Abstract
Perceptions is a study of how a machine perceives a photograph at different layers within its neural network. We generate sets of pen strokes which are drawn by a robot using pen and ink on Bristol board. The illustrations are produced by maximising the similarity between the machine's internal perception of the illustration and chosen target photographs. The study focusses on the difference between different inductive biases (shape versus texture) in the training of the neural network, as well as how the machine's perception changes as a function of depth within its network. The photos chosen are from travels to far away cities, taken before the COVID-19 pandemic.
Image
perceptions_01
- Version of Record
Image
perceptions_02
- Version of Record
Video
Perceptions_03
- Version of Record
Text
perceptions_00
- Other
More information
Accepted/In Press date: 21 October 2021
Published date: 13 December 2021
Venue - Dates:
The AI Art Gallery: NeurIPS Workshop on Machine Learning for Creativity and Design 2021, 2021-12-13
Identifiers
Local EPrints ID: 453147
URI: http://eprints.soton.ac.uk/id/eprint/453147
PURE UUID: ef5a7a38-5292-41a8-9ce3-efc0d3743fbe
Catalogue record
Date deposited: 08 Jan 2022 22:38
Last modified: 17 Mar 2024 03:05
Export record
Contributors
Author:
Daniela Mihai
Author:
Jonathon Hare
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
