Title:
METHOD FOR GENERATING AND LEARNING IMPROVED NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2019/039758
Kind Code:
A1
Abstract:
According to one exemplary embodiment of the present disclosure, a method for generating a neural network model implemented by a computing device may be provided, the method comprising the steps of: generating a first input layer to which a first input is applied; and generating a hidden layer to which an output of the first input layer is applied, wherein the hidden layer includes a second input layer to which a second input is applied. According to one exemplary embodiment of the present disclosure, a method for learning a neural network model implemented by a computing device may be provided, the method comprising the steps of: receiving a training dataset including a first input and a second input; applying the first input to a first input layer; and applying the second input to a second input layer, wherein the second input layer is included in a hidden layer to which an output of the first input layer is applied.
Inventors:
KIM GWANGMIN (KR)
Application Number:
PCT/KR2018/008621
Publication Date:
February 28, 2019
Filing Date:
July 30, 2018
Export Citation:
Assignee:
SUALAB CO LTD (KR)
International Classes:
G06N3/08; G06N3/04
Foreign References:
| US20100169256A1 | 2010-07-01 | |||
| KR20160063965A | 2016-06-07 | |||
| US20160162781A1 | 2016-06-09 | |||
| JP2017049907A | 2017-03-09 |
Other References:
SOO HYUN BAE: "ACOUSTIC SCENE CLASSIFICATION USING PARALLEL COMBINATION OF LSTM AND CNN", DETECTION AND CLASSIFICATION OF ACOUSTIC SCENES AND EVENTS 2016, 3 September 2016 (2016-09-03), pages 1 - 5, XP055579570, Retrieved from the Internet
Attorney, Agent or Firm:
LEE, Dae Ho et al. (KR)
Download PDF: