公开(公告)号：US20200380374A1

公开(公告)日：2020-12-03

申请号：US16601504

申请日：2019-10-14

Applicant: Apple Inc.

Inventor： Cecile M. FORET ,  Xiaozhong YAO ,  Sundararaman HARIHARASUBRAMANIAN

IPC: G06N3/10 ,  G06F8/41 ,  G06F17/16

Abstract: The subject technology receives code corresponding to a neural network (NN) model and a set of weights for the NN model. The subject technology determines a set of layers that are mutable in the NN model. The subject technology determines information for mapping a second set of weights to the set of weights for the NN model. The subject technology generates metadata corresponding to the set of layers that are mutable, and the information for mapping the second set of weights to the set of weights for the NN model, wherein the generated metadata enables updating the set of layers that are mutable during execution of the NN model.

公开(公告)号：US20240296346A1

公开(公告)日：2024-09-05

申请号：US18383858

申请日：2023-10-25

Applicant: Apple Inc.

Inventor： Cecile M. FORET ,  Xiaozhong YAO ,  Sundararaman HARIHARASUBRAMANIAN

IPC: G06N3/10 ,  G06F8/41 ,  G06F17/16

CPC classification number: G06N3/10 ,  G06F8/41 ,  G06F17/16

Abstract: The subject technology receives code corresponding to a neural network (NN) model and a set of weights for the NN model. The subject technology determines a set of layers that are mutable in the NN model. The subject technology determines information for mapping a second set of weights to the set of weights for the NN model. The subject technology generates metadata corresponding to the set of layers that are mutable, and the information for mapping the second set of weights to the set of weights for the NN model, wherein the generated metadata enables updating the set of layers that are mutable during execution of the NN model.

公开(公告)号：US20200379911A1

公开(公告)日：2020-12-03

申请号：US16601501

申请日：2019-10-14

Applicant: Apple Inc.

Inventor： Fabian P. WANNER ,  Cecile M. FORET ,  Xiaozhong YAO ,  Sundararaman HARIHARASUBRAMANIAN

IPC: G06F12/0875 ,  G06N3/04 ,  G06N3/063 ,  G06F12/0891 ,  G06F12/126 ,  G06N3/08 ,  G06F12/084

Abstract: The subject technology receives code corresponding to a neural network (NN) model, the code including particular operations that are performed by the NN model. The subject technology determines, among the particular operations, a set of operations that are to be allocated to a cache of the electronic device that is to execute the NN model. The subject technology generates a set of cache indicators corresponding to the determined set of operations. The subject technology compiles the code and the generated set of cache indicators to provide a compiled binary for the NN model to execute on a target device.