Cargando…
The effects of implementing phenomenology in a deep neural network
There have been several recent attempts at using Artificial Intelligence systems to model aspects of consciousness (Gamez, 2008; Reggia, 2013). Deep Neural Networks have been given additional functionality in the present attempt, allowing them to emulate phenological aspects of consciousness by self...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8214092/ https://www.ncbi.nlm.nih.gov/pubmed/34179532 http://dx.doi.org/10.1016/j.heliyon.2021.e07246 |
_version_ | 1783709988908171264 |
---|---|
author | Bensemann, Joshua Witbrock, Michael |
author_facet | Bensemann, Joshua Witbrock, Michael |
author_sort | Bensemann, Joshua |
collection | PubMed |
description | There have been several recent attempts at using Artificial Intelligence systems to model aspects of consciousness (Gamez, 2008; Reggia, 2013). Deep Neural Networks have been given additional functionality in the present attempt, allowing them to emulate phenological aspects of consciousness by self-generating information representing multi-modal inputs as either sounds or images. We added these functions to determine whether knowledge of the input's modality aids the networks' learning. In some cases, these representations caused the model to be more accurate after training and for less training to be required for the model to reach its highest accuracy scores. |
format | Online Article Text |
id | pubmed-8214092 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-82140922021-06-25 The effects of implementing phenomenology in a deep neural network Bensemann, Joshua Witbrock, Michael Heliyon Research Article There have been several recent attempts at using Artificial Intelligence systems to model aspects of consciousness (Gamez, 2008; Reggia, 2013). Deep Neural Networks have been given additional functionality in the present attempt, allowing them to emulate phenological aspects of consciousness by self-generating information representing multi-modal inputs as either sounds or images. We added these functions to determine whether knowledge of the input's modality aids the networks' learning. In some cases, these representations caused the model to be more accurate after training and for less training to be required for the model to reach its highest accuracy scores. Elsevier 2021-06-08 /pmc/articles/PMC8214092/ /pubmed/34179532 http://dx.doi.org/10.1016/j.heliyon.2021.e07246 Text en © 2021 The Author(s) https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Research Article Bensemann, Joshua Witbrock, Michael The effects of implementing phenomenology in a deep neural network |
title | The effects of implementing phenomenology in a deep neural network |
title_full | The effects of implementing phenomenology in a deep neural network |
title_fullStr | The effects of implementing phenomenology in a deep neural network |
title_full_unstemmed | The effects of implementing phenomenology in a deep neural network |
title_short | The effects of implementing phenomenology in a deep neural network |
title_sort | effects of implementing phenomenology in a deep neural network |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8214092/ https://www.ncbi.nlm.nih.gov/pubmed/34179532 http://dx.doi.org/10.1016/j.heliyon.2021.e07246 |
work_keys_str_mv | AT bensemannjoshua theeffectsofimplementingphenomenologyinadeepneuralnetwork AT witbrockmichael theeffectsofimplementingphenomenologyinadeepneuralnetwork AT bensemannjoshua effectsofimplementingphenomenologyinadeepneuralnetwork AT witbrockmichael effectsofimplementingphenomenologyinadeepneuralnetwork |