-
1.发明申请公开(公告)号：US20200226199A1
公开(公告)日：2020-07-16
申请号：US16244707
申请日：2019-01-10
Applicant: Nokia Technologies OY
Inventor： Iraj SANIEE , Christos MAVRIDIS
Abstract: The method includes compiling data into mutual information columns, determining mutual information for each pairing of the mutual information columns and creating a matrix using the mutual information, the matrix including a first set of data columns, wherein each of the first set of data columns represents at least one feature of the data. The method further includes computing eigenvalues and eigenvectors of the matrix, ordering the eigenvalues using an absolute value of the eigenvalues, iteratively selecting at least one second set of data columns by successively removing data columns from the first set of data columns based on the ordered eigenvalues, and controlling an operation of an electronic device based on the at least one second set of data.
-
公开(公告)号：US20210397965A1
公开(公告)日：2021-12-23
申请号：US17354398
申请日：2021-06-22
Applicant: Nokia Technologies Oy
Inventor： Honglei ZHANG , Francesco CRICRI , Hamed REZAZADEGAN TAVAKOLI , Joachim WABNIG , Iraj SANIEE , Miska Matias HANNUKSELA , Emre AKSU
Abstract: An apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: estimate an importance of parameters of a neural network based on a graph diffusion process over at least one layer of the neural network; determine the parameters of the neural network that are suitable for pruning or sparsification; remove neurons of the neural network to prune or sparsify the neural network; and provide at least one syntax element for signaling the pruned or sparsified neural network over a communication channel, wherein the at least one syntax element comprises at least one neural network representation syntax element.
-
Search Results
2
records
(took 0.01 seconds)
