Patent · US Active

Adjusting activation compression for neural network training

US12165038B2 · kind B2 · utility

0Cited by
8References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 14, 2019
Grant dateDec 10, 2024
Priority date
Expiry dateAug 8, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/048
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Apparatus and methods for training a neural network accelerator using quantized precision data formats are disclosed, and, in particular, for adjusting floating-point formats used to store activation values during training. In certain examples of the disclosed technology, a computing system includes processors, memory, and a floating-point compressor in communication with the memory. The computing system is configured to produce a neural network comprising activation values expressed in a first floating-point format, select a second floating-point format for the neural network based on a performance metric, convert at least one of the activation values to the second floating-point format, and store the compressed activation values in the memory. Aspects of the second floating-point format that can be adjusted include the number of bits used to express mantissas, exponent format, use of non-uniform mantissas, and/or use of outlier values to express some of the mantissas.

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