Patent · US Active

Knowledge distillation and gradient pruning-based compression of artificial intelligence-based base caller

US12354008B2 · kind B2 · utility

0Cited by
43References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 15, 2021
Grant dateJul 8, 2025
Priority date
Expiry dateJan 14, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG16B40/20
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The technology disclosed compresses a larger, teacher base caller into a smaller, student base caller. The student base caller has fewer processing modules and parameters than the teacher base caller. The teacher base caller is trained using hard labels (e.g., one-hot encodings). The trained teacher base caller is used to generate soft labels as output probabilities during the inference phase. The soft labels are used to train the student base caller.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.