Invention Grant
- Patent Title: Convolutional neural network architecture with adaptive filters
-
Application No.: US16038830Application Date: 2018-07-18
-
Publication No.: US11227108B2Publication Date: 2022-01-18
- Inventor: Renqiang Min , Dinghan Shen , Yitong Li
- Applicant: NEC Laboratories America, Inc.
- Applicant Address: US NJ Princeton
- Assignee: NEC Laboratories America, Inc.
- Current Assignee: NEC Laboratories America, Inc.
- Current Assignee Address: US NJ Princeton
- Agent Joseph Kolodka
- Main IPC: G06N3/04
- IPC: G06N3/04 ; G06N5/04 ; G06F16/35 ; G06N3/08 ; G06F40/20 ; H03M7/30 ; G06F16/332 ; G06F16/33 ; G06F16/335 ; H04L12/58

Abstract:
A computer-implemented method for employing input-conditioned filters to perform natural language processing tasks using a convolutional neural network architecture includes receiving one or more inputs, generating one or more sets of filters conditioned on respective ones of the one or more inputs by implementing one or more encoders to encode the one or more inputs into one or more respective hidden vectors, and implementing one or more decoders to determine the one or more sets of filters based on the one or more hidden vectors, and performing adaptive convolution by applying the one or more sets of filters to respective ones of the one or more inputs to generate one or more representations.
Public/Granted literature
- US20190079915A1 CONVOLUTIONAL NEURAL NETWORK ARCHITECTURE WITH ADAPTIVE FILTERS Public/Granted day:2019-03-14
Information query