Deep learning framework decodes sex from prehistoric hand stencils

Researchers have developed a novel deep learning framework designed to determine the biological sex of individuals who created prehistoric hand stencils. This uncertainty-aware system addresses challenges like the lack of ground truth and population differences by explicitly modeling and propagating uncertainty. The methodology involves image processing, contour extraction, and ensemble predictions from multiple neural networks, validated through manifold mapping and explainable AI techniques. AI

IMPACT This research demonstrates a novel application of deep learning for archaeological inference, potentially enabling more robust analysis of ancient artifacts.

RANK_REASON The cluster contains an academic paper detailing a new methodology for applying deep learning to an archaeological problem. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Boris Mederos Phd
• EfficientNet-B3
• k-nearest neighbors algorithm
• LayerCAM
• MobileViT-S
• Uniform Manifold Approximation and Projection
• Upper Paleolithic

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →