Invention Application
US20170076196A1 COMPRESSED RECURRENT NEURAL NETWORK MODELS 审中-公开
压缩性循环神经网络模型

  • Patent Title: COMPRESSED RECURRENT NEURAL NETWORK MODELS
  • Patent Title (中): 压缩性循环神经网络模型
  • Application No.: US15172457
    Application Date: 2016-06-03
  • Publication No.: US20170076196A1
    Publication Date: 2017-03-16
  • Inventor: Tara N. SainathVikas Sindhwani
  • Applicant: Google Inc.
  • Main IPC: G06N3/04
  • IPC: G06N3/04 G06N3/08
COMPRESSED RECURRENT NEURAL NETWORK MODELS
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing long-short term memory layers with compressed gating functions. One of the systems includes a first long short-term memory (LSTM) layer, wherein the first LSTM layer is configured to, for each of the plurality of time steps, generate a new layer state and a new layer output by applying a plurality of gates to a current layer input, a current layer state, and a current layer output, each of the plurality of gates being configured to, for each of the plurality of time steps, generate a respective intermediate gate output vector by multiplying a gate input vector and a gate parameter matrix. The gate parameter matrix for at least one of the plurality of gates is a structured matrix or is defined by a compressed parameter matrix and a projection matrix.
Public/Granted literature
Information query
Patent Agency Ranking
0/0