-
公开(公告)号：US11580408B2
公开(公告)日：2023-02-14
申请号：US16830566
申请日：2020-03-26
发明人： Xiangxiang Chu , Ruijun Xu , Bo Zhang , Jixiang Li , Qingyuan Li
摘要： A search method for a neural network model structure, includes: generating an initial generation population of network model structure based on multi-objective optimization hyper parameters, as a current generation population of network model structure; performing selection and crossover on the current generation population of network model structure; generating a part of network model structure based on reinforcement learning mutation, and generating a remaining part of network model structure based on random mutation on the selected and crossed network model structure; generating a new population of network model structure based on the part of network model structure generated by reinforcement learning mutation and the remaining part of network model structure generated by random mutation; and searching a next generation population of network model structure based on the current generation population of network model structure and the new population of network model structure.
-
公开(公告)号：US20210142166A1
公开(公告)日：2021-05-13
申请号：US16828427
申请日：2020-03-24
发明人： Xiangxiang Chu , Bo Zhang , Ruijun Xu , Bin Wang
摘要： A hypernetwork training method includes: acquiring a multipath neural subnetwork based on a preconstructed initial hypernetwork; training the multipath neural subnetwork to update a weight parameter of each substructure in the multipath neural subnetwork; synchronizing the weight parameter of each substructure in the multipath neural subnetwork to the preconstructed initial hypernetwork; and determining whether the preconstructed initial hypernetwork converges, and if it is determined that the preconstructed initial hypernetwork does not converge, re-executing the acquiring, the training, the synchronizing, and the determining, to obtain a target hypernetwork.
-
公开(公告)号：US11443189B2
公开(公告)日：2022-09-13
申请号：US16828427
申请日：2020-03-24
发明人： Xiangxiang Chu , Bo Zhang , Ruijun Xu , Bin Wang
摘要： A hypernetwork training method includes: acquiring a multipath neural subnetwork based on a preconstructed initial hypernetwork; training the multipath neural subnetwork to update a weight parameter of each substructure in the multipath neural subnetwork; synchronizing the weight parameter of each substructure in the multipath neural subnetwork to the preconstructed initial hypernetwork; and determining whether the preconstructed initial hypernetwork converges, and if it is determined that the preconstructed initial hypernetwork does not converge, re-executing the acquiring, the training, the synchronizing, and the determining, to obtain a target hypernetwork.
-
公开(公告)号：US20210133563A1
公开(公告)日：2021-05-06
申请号：US16744674
申请日：2020-01-16
发明人： Xiangxiang Chu , Ruijun Xu , Bo Zhang , Jixiang Li , Qingyuan Li , Bin Wang
摘要： A method for training a neural network, includes: training a super network to obtain a network parameter of the super network, wherein each network layer of the super network includes multiple candidate network sub-structures in parallel; for each network layer of the super network, selecting, from the multiple candidate network sub-structures, a candidate network sub-structure to be a target network sub-structure; constructing a sub-network based on target network sub-structures each selected in a respective network layer of the super network; and training the sub-network, by taking the network parameter inherited from the super network as an initial parameter of the sub-network, to obtain a network parameter of the sub-network.
-
公开(公告)号：US11663468B2
公开(公告)日：2023-05-30
申请号：US16744674
申请日：2020-01-16
发明人： Xiangxiang Chu , Ruijun Xu , Bo Zhang , Jixiang Li , Qingyuan Li , Bin Wang
摘要： A method for training a neural network, includes: training a super network to obtain a network parameter of the super network, wherein each network layer of the super network includes multiple candidate network sub-structures in parallel; for each network layer of the super network, selecting, from the multiple candidate network sub-structures, a candidate network sub-structure to be a target network sub-structure; constructing a sub-network based on target network sub-structures each selected in a respective network layer of the super network; and training the sub-network, by taking the network parameter inherited from the super network as an initial parameter of the sub-network, to obtain a network parameter of the sub-network.
-
-
-
-
搜索结果
5 条记录 (耗时 0.015 秒)
