AI-ncient Pottery: Northern Arizona University Researchers Use Machine Learning to Study Distant Cultures

Chris Downum and Leszek Pawlowicz, researchers in the Department of Anthropology at Northern Arizona University, are utilizing GPU-based deep learning algorithms to classify sherds– small pieces of ancient pottery.

The more advanced modern technologies end up being, the more they can assist us comprehend the past.

They talked with NVIDIA AI Podcast host Noah Kravitz about examining sherds to find out more about American Southwest culture, circa 825 to 1300 A.D.

Key Points From This Episode:

For almost a century, archaeologists have carefully analyzed sherds to determine their time periods and cultural affiliations. Human interpretations of the very same sherd frequently vary– driven by uncertainty, simple differences in opinion and a lack of familiarity with the millions of pottery typologies that exist. Downum and Pawlowicz utilize maker finding out to help researchers and students more objectively categorize these ancient pottery pieces.
Neural networks, trained on massive image datasets of sherds that were categorized in contract with professional archaeologists, determine a sherds typology. Results are displayed with “heat maps” which highlight sections of the sherd that the AI design found most essential to its characterization.

Tweetables:

5:22]

Device knowing “includes a great deal of objectivity and dependability to the process of classifying intricate artifacts.”– Chris Downum [18:43]

You Might Also Like:

Wild Things: NVIDIAs Sifei Liu Talks 3D Reconstructions of Endangered Species

Endangered species can be challenging to study, as they are elusive and the really act of observing them can disrupt their lives. Now, researchers can take a closer look at threatened types by studying AI-generated 3D representations of them.

Waste Not, Want Not: AI Startup Opseyes Revolutionizes Wastewater Analysis

What do radiology and wastewater share? Ideally, not much. However at startup Opseyes, creator Bryan Arndt and information researcher Robin Schlenga are using the AI reinventing medical imaging to examine wastewater samples.

Say Yes to the AI Dress: Entrepreneur Brings GPUs to Fashion

In the future imagined by Pinar Yanardag, a postdoctoral research partner at MIT Media Lab, AI will work together with human beings, not replace them. This is the principle behind her project, “How to Generate (Almost) Anything.”

Register for the AI Podcast

Get the AI Podcast through iTunes, Google Podcasts, Google Play, Castbox, DoggCatcher, Overcast, PlayerFM, Pocket Casts, Podbay, PodBean, PodCruncher, PodKicker, Soundcloud, Spotify, Stitcher and TuneIn. Drop us a note if your favorite isnt listed here.

Make the AI Podcast Better

For almost a century, archaeologists have actually carefully taken a look at sherds to determine their time durations and cultural affiliations. Human interpretations of the exact same sherd typically differ– driven by obscurity, simple distinctions in viewpoint and an absence of familiarity with the millions of pottery typologies that exist. Downum and Pawlowicz use maker learning to assist researchers and students more objectively classify these ancient pottery fragments.
At start-up Opseyes, creator Bryan Arndt and information researcher Robin Schlenga are using the AI revolutionizing medical imaging to analyze wastewater samples.

Your answers will help us make a much better podcast.

Have a couple of minutes to spare? Fill out this listener survey. Your responses will assist us make a better podcast.

Leave a Reply

Your email address will not be published. Required fields are marked *