Applying supervised deep transfer learning convolutional neural networks to the classification of palaeoenvironmental remains

Applying supervised deep transfer learning convolutional neural networks to the classification of palaeoenvironmental remains

Project description

This doctoral thesis is an interdisciplinary investigation of the subjectivity inherent in the analysts’ classifications of palaeoenvironmental remains, namely pollen grains and faunal osseous remains. The significant research contributions span from improvements in the post-hoc interpretation of convolutional neural networks, state-of-the-art classification models in pollen classification, and the first application of convolutional neural networks in the classification of bones to species from images.
Show more

Starting year

2022

Granted funding

Ilkka Sipilä
15 000 €

Funder

Kone Foundation

Funding instrument

Ph.D work

Call

Apurahahaku

Other information

Funding decision number

Koneen Säätiö_202102207

Fields of science

History and archaeology

Themes

Tietotekniikka

Keywords

Arkeologia, Arkeologisten esineiden tunnistus, Automaatio, Tieteidenvälinen tutkimus, Koneoppiminen

Identified topics

artificial intelligence, machine learning