AUTOMATED GENERATION OF NEURAL NETWORKS

专利名称：AUTOMATED GENERATION OF NEURAL

NETWORKS

发明人：MOLONEY, David Macdara,XU,

Xiaofan,CETTO, Tomaso F.L.,BYRNE, JonathanDavid

申请号：EP19878027.2申请日：20191031公开号：EP3874413A1公开日：20210908

摘要：A grammar is used in a grammatical evolution of a set of parent neural networkmodels to generate a set of child neural network models. A generation of neuralnetwork models is tested based on a set of test data, where the generation includes theset of child neural network models. Respective values for each one of a plurality ofattributes are determined for each neural network in the generation, where one of theattributes includes a validation accuracy value determined from the test. Multi-objectiveoptimization is performed based on the values of the plurality of attributes for thegeneration of neural networks and a subset of the generation of neural network modelsis selected based on the results of the multi-objective optimization.

申请人：MOVIDIUS LTD.

地址：Capronilaan 37 1119 NG Schiphol-Rijk NL

国籍：NL

代理机构：Goddar, Heinz J.

更多信息请下载全文后查看