Academic Paper

Rethinking Streaming Machine Learning Evaluation

May, 2022

Abstract

While most work on evaluating machine learning (ML) models focuses on computing accuracy on batches of data, tracking accuracy alone in a streaming setting (i.e., unbounded, timestamp-ordered datasets) fails to appropriately identify when models are performing unexpectedly. In this position paper, we discuss how the nature of streaming ML problems introduces new real-world challenges (e.g., delayed arrival of labels) and recommend additional metrics to assess streaming ML performance.

Look-alike humans identified by facial recognition algorithms show genetic similarities

August, 2022

Highlights

  • Facial recognition algorithms identify “look-alike” humans for multiomics studies
  • Intrapair look-alikes share common genetic sequences such as face trait variants
  • DNA methylation and microbiome profiles only contribute modestly to human likeness
  • The identified SNPs impact physical and behavioral phenotypes beyond facial features

Summary

Pages