US 12,217,185 B2
Method and apparatus of increasing knowledge based on uncertainty in neural networks
Hyun Woo Kim, Daejeon (KR); Jeon Gue Park, Daejeon (KR); Hwa Jeon Song, Daejeon (KR); Yoo Rhee Oh, Daejeon (KR); Byung Hyun Yoo, Daejeon (KR); Eui Sok Chung, Daejeon (KR); and Ran Han, Daejeon (KR)
Assigned to ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed by Electronics and Telecommunications Research Institute, Daejeon (KR)
Filed on May 27, 2021, as Appl. No. 17/332,464.
Claims priority of application No. 10-2020-0065489 (KR), filed on May 29, 2020.
Prior Publication US 2021/0374545 A1, Dec. 2, 2021
Int. Cl. G06N 3/082 (2023.01); G06F 40/35 (2020.01); G06N 3/042 (2023.01); G06N 5/022 (2023.01); G06N 5/043 (2023.01)
CPC G06N 3/082 (2013.01) [G06F 40/35 (2020.01); G06N 3/042 (2023.01); G06N 5/022 (2013.01); G06N 5/043 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method of increasing knowledge based on uncertainty of a neural network in an artificial intelligence (AI) agent, programmed and executed by a computing device to include a knowledge generating neural network for generating knowledge about a user query and a dialogue generating neural network for generating an answer to the user query on the basis of the knowledge, the method comprising:
converting each of a current user query, previous knowledge generated by the knowledge generating neural network, and a previous answer, generated by the dialogue generating neural network, into an embedding vector value having a specific dimension;
calculating a plurality of output values corresponding to the embedding vector value by using the knowledge generating neural network with a dropout technique applied thereto and calculating uncertainty of the knowledge generating neural network on the basis of the calculated plurality of output values; and
performing linear conversion on the calculated uncertainty to calculate a compensation value, obtain learning data having the calculated compensation value from a database built through unsupervised learning, and training the knowledge generating neural network and the dialogue generating neural network on the basis of the obtained learning data to increase knowledge.