ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

특허 검색
구분 출원국
출원년도 ~ 키워드

상세정보

등록 선형 근사화된 심층 신경망 모델

선형 근사화된 심층 신경망 모델
이미지 확대
발명자
정훈, 이윤근, 이성주, 박전규
출원번호
16121836 (2018.09.05)
공개번호
20190272309 (2019.09.05)
등록번호
10789332 (2020.09.29)
출원국
미국
협약과제
17HS5700, 언어학습을 위한 자유발화형 음성대화처리 원천기술 개발, 이윤근
초록
Provided are an apparatus and method for linearly approximating a deep neural network (DNN) model which is a non-linear function. In general, a DNN model shows good performance in generation or classification tasks. However, the DNN fundamentally has non-linear characteristics, and therefore it is difficult to interpret how a result from inputs given to a black box model has been derived. To solve this problem, linear approximation of a DNN is proposed. The method for linearly approximating a DNN model includes 1) converting a neuron constituting a DNN into a polynomial, and 2) classifying the obtained polynomial as a polynomial of input signals and a polynomial of weights.
KSP 제안 키워드
Black Box, Black box model, Box model, Deep neural network(DNN), Linear approximation, Linear function, Network model, Neural networks, Nonlinear characteristics, neural network model, non-linear, nonlinear function