[Rockhounds] Archaeologists train computer to sort prehistoric pottery sherds

[Paul]

Archaeologists train a neural network to sort pottery fragments for them
The network turned out to be as good at the job as human archaeologists.
Kiona N. Smith, Ars Technical, May 21, 2021
https://arstechnica.com/science/2021/05/archaeologists-train-a-neural-network-to-sort-pottery-fragments-for-them/

The paper is:

Pawlowicz, L.M. and Downum, C.E., 2021. Applications of deep learning
to decorated ceramic typology and classification: A case study using
Tusayan White Ware from Northeast Arizona. Journal of Archaeological
Science, 130, no.105375.

Another paper is:

Aprile, A., Castellano, G. and Eramo, G., 2014. Combining image analysis
and modular neural networks for classification of mineral inclusions and
pores in archaeological potsherds. Journal of archaeological science,
50, pp.262-272.
https://www.sciencedirect.com/science/article/pii/S0305440314002635
https://www.socminpet.it/dwl.php?file=files/download/vol-40/Aprile.pdf

Yours,

Paul H.