A proof of concept for machine learning-based virtual knapping using neural networks

Abstract Prehistoric stone tools are an important source of evidence for the study of human behavioural and cognitive evolution. Archaeologists use insights from the experimental replication of lithics to understand phenomena such as the behaviours and cognitive capacities required to manufacture th...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jordy Didier Orellana Figueroa, Jonathan Scott Reeves, Shannon P. McPherron, Claudio Tennie
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/faa7963ae11740449c1faf5f3832bb7c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:faa7963ae11740449c1faf5f3832bb7c
record_format	dspace
spelling	oai:doaj.org-article:faa7963ae11740449c1faf5f3832bb7c2021-12-02T18:37:11ZA proof of concept for machine learning-based virtual knapping using neural networks10.1038/s41598-021-98755-62045-2322https://doaj.org/article/faa7963ae11740449c1faf5f3832bb7c2021-10-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-98755-6https://doaj.org/toc/2045-2322Abstract Prehistoric stone tools are an important source of evidence for the study of human behavioural and cognitive evolution. Archaeologists use insights from the experimental replication of lithics to understand phenomena such as the behaviours and cognitive capacities required to manufacture them. However, such experiments can require large amounts of time and raw materials, and achieving sufficient control of key variables can be difficult. A computer program able to accurately simulate stone tool production would make lithic experimentation faster, more accessible, reproducible, less biased, and may lead to reliable insights into the factors that structure the archaeological record. We present here a proof of concept for a machine learning-based virtual knapping framework capable of quickly and accurately predicting flake removals from 3D cores using a conditional adversarial neural network (CGAN). We programmatically generated a testing dataset of standardised 3D cores with flakes knapped from them. After training, the CGAN accurately predicted the length, volume, width, and shape of these flake removals using the intact core surface information alone. This demonstrates the feasibility of machine learning for investigating lithic production virtually. With a larger training sample and validation against archaeological data, virtual knapping could enable fast, cheap, and highly-reproducible virtual lithic experimentation.Jordy Didier Orellana FigueroaJonathan Scott ReevesShannon P. McPherronClaudio TennieNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Jordy Didier Orellana Figueroa Jonathan Scott Reeves Shannon P. McPherron Claudio Tennie A proof of concept for machine learning-based virtual knapping using neural networks
description	Abstract Prehistoric stone tools are an important source of evidence for the study of human behavioural and cognitive evolution. Archaeologists use insights from the experimental replication of lithics to understand phenomena such as the behaviours and cognitive capacities required to manufacture them. However, such experiments can require large amounts of time and raw materials, and achieving sufficient control of key variables can be difficult. A computer program able to accurately simulate stone tool production would make lithic experimentation faster, more accessible, reproducible, less biased, and may lead to reliable insights into the factors that structure the archaeological record. We present here a proof of concept for a machine learning-based virtual knapping framework capable of quickly and accurately predicting flake removals from 3D cores using a conditional adversarial neural network (CGAN). We programmatically generated a testing dataset of standardised 3D cores with flakes knapped from them. After training, the CGAN accurately predicted the length, volume, width, and shape of these flake removals using the intact core surface information alone. This demonstrates the feasibility of machine learning for investigating lithic production virtually. With a larger training sample and validation against archaeological data, virtual knapping could enable fast, cheap, and highly-reproducible virtual lithic experimentation.
format	article
author	Jordy Didier Orellana Figueroa Jonathan Scott Reeves Shannon P. McPherron Claudio Tennie
author_facet	Jordy Didier Orellana Figueroa Jonathan Scott Reeves Shannon P. McPherron Claudio Tennie
author_sort	Jordy Didier Orellana Figueroa
title	A proof of concept for machine learning-based virtual knapping using neural networks
title_short	A proof of concept for machine learning-based virtual knapping using neural networks
title_full	A proof of concept for machine learning-based virtual knapping using neural networks
title_fullStr	A proof of concept for machine learning-based virtual knapping using neural networks
title_full_unstemmed	A proof of concept for machine learning-based virtual knapping using neural networks
title_sort	proof of concept for machine learning-based virtual knapping using neural networks
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/faa7963ae11740449c1faf5f3832bb7c
work_keys_str_mv	AT jordydidierorellanafigueroa aproofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT jonathanscottreeves aproofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT shannonpmcpherron aproofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT claudiotennie aproofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT jordydidierorellanafigueroa proofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT jonathanscottreeves proofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT shannonpmcpherron proofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks AT claudiotennie proofofconceptformachinelearningbasedvirtualknappingusingneuralnetworks
_version_	1718377838989541376

A proof of concept for machine learning-based virtual knapping using neural networks

Ejemplares similares