Invention Grant
- Patent Title: Neural networks for transforming signals
-
Application No.: US15342252Application Date: 2016-11-03
-
Publication No.: US10592800B2Publication Date: 2020-03-17
- Inventor: John Hershey , Jonathan Le Roux , Felix Weninger
- Applicant: Mitsubishi Electric Research Laboratories, Inc.
- Applicant Address: US MA Cambridge
- Assignee: Mitsubishi Electric Research Laboratories, Inc.
- Current Assignee: Mitsubishi Electric Research Laboratories, Inc.
- Current Assignee Address: US MA Cambridge
- Agent Gennadiy Vinokur; James McAleenan; Hironori Tsukamoto
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N20/00 ; G06N3/08 ; G06N7/00 ; G10L15/16

Abstract:
A method for transforms input signals, by first defining a model for transforming the input signals, wherein the model is specified by constraints and a set of model parameters. An iterative inference procedure is derived from the model and the set of model parameters and unfolded into a set of layers, wherein there is one layer for each iteration of the procedure, and wherein a same set of network parameters is used by all layers. A neural network is formed by untying the set of network parameters such that there is one set of network parameters for each layer and each set of network parameters is separately maintainable and separately applicable to the corresponding layer. The neural network is trained to obtain a trained neural network, and then input signals are transformed using the trained neural network to obtain output signals.
Public/Granted literature
- US20170053203A1 Neural Networks for Transforming Signals Public/Granted day:2017-02-23
Information query