Abstract
Deep learning is a powerful tool for exploring large datasets and discovering new patterns. This work presents an account of a metric learning-based deep convolutional neural network (CNN) applied to an archaeological dataset. The proposed account speaks of three stages: training, testing/validating, and community detection. Several thousand artefact images, ranging from the Lower Palaeolithic period (1.4 million years ago) to the Late Islamic period (fourteenth century AD), were used to train the model (i.e., the CNN), to discern artefacts by site and period. After training, it attained a comparable accuracy to archaeologists in various periods. In order to test the model, it was called to identify new query images according to similarities with known (training) images. Validation blinding experiments showed that while archaeologists performed as well as the model within their field of expertise, they fell behind concerning other periods. Lastly, a community detection algorithm based on the confusion matrix data was used to discern affiliations across sites. A case-study on Levantine Natufian artefacts demonstrated the algorithm’s capacity to discern meaningful connections. As such, the model has the potential to reveal yet unknown patterns in archaeological data.
Highlights
Archaeology, broadly defined, is the study of the human past through material remains: artefacts of various materials that were manufactured, used, and discarded by ancient societies (Murray and Evans, 2008; Renfrew and Bahn, 2013)
In order to automate this process and utilise computers’ excellent pattern recognition capabilities, efforts have been made to incorporate computer applications into the processes of archaeological classifications (Derech et al, 2021; Tal, 2014). Notable among these are experimentations with machine learning models—computer algorithms that learn from data how to automatically detect patterns and make accurate decisions (Mitchell, 1997; Bishop, 2006; Duda and Hart, 1973)
Several attempts were made to apply machine learning to archaeological materials (Barcelo, 2008, 2016; Barceló and Bogdanovic, 2015; Díez-Pastor et al, 2018; Macleod, 2018)
Summary
Archaeology, broadly defined, is the study of the human past through material remains: artefacts of various materials (e.g., stone, bone, pottery, metal, glass) that were manufactured, used, and discarded by ancient societies (Murray and Evans, 2008; Renfrew and Bahn, 2013). The first and most basic task of the field’s practitioners is to properly classify the numerous artefacts they encounter, determining their date, cultural attribution, form, function, socio-economic significance, and other features (Arkadiev, 2020; Dunnell, 1993; Hermon et al, 2004; Krieger, 1944; Whittaker et al, 1998) Such classifications often depend on prior knowledge, expertise, and preference for certain visual criteria over others (Barcelo, 1995). In order to automate this process and utilise computers’ excellent pattern recognition capabilities, efforts have been made to incorporate computer applications into the processes of archaeological classifications (Derech et al, 2021; Tal, 2014) Notable among these are experimentations with machine learning models—computer algorithms that learn from data how to automatically detect patterns and make accurate decisions (Mitchell, 1997; Bishop, 2006; Duda and Hart, 1973). For instance, Agam et al (2020) combined Raman spectroscopy with machine learning algorithms to quantitatively estimate different degrees of thermal alteration on flint artefacts
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
