US 11,928,581 B2
System and method for compressing kernels
Daren Croxford, Swaffham Prior (GB); Jayavarapu Srinivasa Rao, Cambridge (GB); and Sharjeel Saeed, Cambridge (GB)
Assigned to Arm Limited, Cambridge (GB)
Filed by Apical Ltd, Cambridge (GB); and Arm Limited, Cambridge (GB)
Filed on Sep. 14, 2018, as Appl. No. 16/132,015.
Prior Publication US 2020/0090032 A1, Mar. 19, 2020
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method of compressing kernels of a neural network trained for a particular purpose; the method comprising:
detecting a plurality of replicated kernels, wherein the plurality of replicated kernels exhibit cyclic rotation;
generating a plurality of composite kernels from the plurality of replicated kernels, the composite kernels comprising kernel data and meta data, wherein generating the plurality of composite kernels comprises determining differences between first replicated kernels and second replicated kernels of the plurality of replicated kernels, wherein at least one of the differences exceeds a predetermined threshold that is indicative of a maximum between the plurality of replicated kernels, and at least one of the differences is less than the predetermined threshold,
wherein at least one of the generated plurality of composite kernels is the second replicated kernel for the at least one of the differences that exceeds the predetermined threshold, and at least one other of the plurality of composite kernels is set to an average of the plurality of replicated kernels for the at least one of the differences that is less than the predetermined threshold; and
storing the plurality of composite kernels.