SYSTEM AND METHOD FOR NEURAL NETWORK
ORCHESTRATION
申请(专利)号： US202416294781
专利号： US2024075019A1 主分类号： G10L15/32
申请日： 2024-03-06 公开公告日： 2024-03-05
分类号： G10L15/32;
申请权利人： 公开国代码： 优先权国家： VERITONE, INC.
US US
发明设计人： 申请国代码： 优先权： G06F17/27; G10L15/02; G10L15/18; G06N3/08; G10L15/16; G10L15/30; G06N5; G06N20; G06N3/04
CHAD STEELBERG;
PETER NGUYEN; DAVID KETTLER; KARL SCHWAMB; YU ZHAO US
20170802 US
201762540508; 20240306 US 202416294781; 20240108 US 202416243033; 20240822 US 202416109516; 20240801 US 202416052459; 20240802 US 202462713937; 20240924 US 202462735769; 20240305 US 202462638745; 20240220 US
202462633023
摘 要：
Methods and systems for training an engine prediction neural network is disclosed. One of the methods can include: extracting image features of a first ground truth image using outputs of one or more layers of an image
classification neural network; classifying the first ground truth image using a plurality of candidate neural networks; determining a classification accuracy score of a classification result of the first ground truth image for each candidate neural network of the plurality of
candidate neural networks; and training the engine prediction neural network to predict the best candidate engine by
associating the image features of the first ground truth image with the classification accuracy score of each candidate neural network. 主权项：
1. A method for training an engine prediction neural network to identify a best ca
摘 要 附 图：
权 利 要 求 说 明 书
【SYSTEM AND METHOD FOR NEURAL NETWORK ORCHESTRATION】的权利说明书内容是......请下载后查看
SYSTEM AND METHOD FOR NEURAL NETWORK ORCHESTRATION
