ETRI-Knowledge Sharing Plaform

KOREAN
특허 검색
Status Country
Year ~ Keyword

Detail

Registered APPARATUS AND METHOD FOR LINEARLY APPROXIMATING DEEP NEURAL NETWORK MODEL

선형 근사화된 심층 신경망 모델
이미지 확대
Inventors
Chung Hoon, Lee Yunkeun, Sung Joo Lee, Park Jeon Gue
Application No.
16121836 (2018.09.05)
Publication No.
20190272309 (2019.09.05)
Registration No.
10789332 (2020.09.29)
Country
UNITED STATES
Project Code
17HS5700, Core technology development of the spontaneous speech dialogue processing for the language learning, Lee Yunkeun
Abstract
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 Keywords
Black Box, Black box model, Box model, Deep neural network(DNN), Linear approximation, Linear function, Network model, Nonlinear characteristics, neural network, neural network model, non-linear, nonlinear function