Patent · US Active

Deep convex network with joint use of nonlinear random projection, restricted boltzmann machine and batch-based parallelizable optimization

US9390371B2 · kind B2 · utility

3Cited by
5References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 17, 2013
Grant dateJul 12, 2016
Priority date
Expiry dateJan 6, 2035

Classification

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

Abstract

A method is disclosed herein that includes an act of causing a processor to access a deep-structured, layered or hierarchical model, called a deep convex network, retained in a computer-readable medium, wherein the deep-structured model comprises a plurality of layers with weights assigned thereto. This layered model can produce the output serving as the scores to combine with transition probabilities between states in a hidden Markov model and language model scores to form a full speech recognizer. Batch-based, convex optimization is performed to learn a portion of the deep convex network's weights, rendering it appropriate for parallel computation to accomplish the training. The method can further include the act of jointly substantially optimizing the weights, the transition probabilities, and the language model scores of the deep-structured model using the optimization criterion based on a sequence rather than a set of unrelated frames.

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