Patent · US Active

Systems and methods for trace norm regularization and faster inference for embedded models

US11556775B2 · kind B2 · utility

0Cited by
5References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 3, 2018
Grant dateJan 17, 2023
Priority date
Expiry dateNov 14, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/16
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Described herein are systems and methods for compressing and speeding up dense matrix multiplications as found, for examples, in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR). For compression, trace norm regularization technique embodiments were introduced and studied for training low rank factored versions of matrix multiplications. Compared to standard low rank training, the methods more consistently lead to good accuracy versus number of parameter trade-offs and can be used to speed-up training of large models. Faster inference may be further enabled on ARM processors through kernels optimized for small batch sizes, resulting in speed ups over the currently used library. Beyond LVCSR, the techniques are also generally applicable to embedded neural networks with large fully connected or recurrent layers.

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