公开(公告)号：US11887225B2

公开(公告)日：2024-01-30

申请号：US17308032

申请日：2021-05-04

Applicant: Apple Inc.

Inventor： Hessam Bagherinezhad ,  Maxwell Horton ,  Mohammad Rastegari ,  Ali Farhadi

IPC: G06N3/04 ,  G06T11/60 ,  G06N3/08 ,  G06F18/214 ,  G06F18/241 ,  G06N3/045 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44 ,  G06V20/52 ,  G06V40/10 ,  G06V20/68

CPC classification number: G06T11/60 ,  G06F18/2148 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/52 ,  G06V40/10 ,  G06T2210/22 ,  G06V20/68

Abstract: Systems and methods are disclosed for training neural networks using labels for training data that are dynamically refined using neural networks and using these trained neural networks to perform detection and/or classification of one or more objects appearing in an image. Particular embodiments may generate a set of crops of images from a corpus of images, then apply a first neural network to the set of crops to obtain a set of respective outputs. A second neural network may then be trained using the set of crops as training examples. The set of respective outputs may be applied as labels for the set of crops.

公开(公告)号：US12020179B2

公开(公告)日：2024-06-25

申请号：US17583133

申请日：2022-01-24

Applicant: Apple Inc.

Inventor： Alexander James Oscar Craver Kirchhoff ,  Ali Farhadi ,  Anish Jnyaneshwar Prabhu ,  Carlo Eduardo Cabanero Del Mundo ,  Daniel Carl Tormoen ,  Hessam Bagherinezhad ,  Matthew S. Weaver ,  Maxwell Christian Horton ,  Mohammad Rastegari ,  Robert Stephen Karl, Jr. ,  Sophie Lebrecht

IPC: G06N5/043 ,  G06F8/10 ,  G06F8/41 ,  G06F11/34 ,  H04N23/611 ,  H04N23/62

CPC classification number: G06N5/043 ,  G06F8/10 ,  G06F8/41 ,  G06F11/3428 ,  H04N23/611 ,  H04N23/62

Abstract: In one embodiment, a method includes providing, to a client system of a user, a user interface for display. The user interface may include a first set of options for selecting an artificial intelligence (AI) task for integrating into a user application, a second set of options for selecting one or more devices on which the user wants to deploy the selected AI task, and a third set of options for selecting one or more performance constraints specific to the selected devices. User specifications may be received based on user selections in the first, second, and third sets of options. A custom AI model may be generated based on the user specifications and sent to the client system of the user for integrating into the user application. The custom AI model once integrated may enable the user application to perform the selected AI task on the selected devices.

公开(公告)号：US11354538B2

公开(公告)日：2022-06-07

申请号：US16908570

申请日：2020-06-22

Applicant: Apple Inc.

Inventor： Hessam Bagherinezhad ,  Ali Farhadi ,  Mohammad Rastegari

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/063 ,  G06N3/04 ,  G06V20/00

Abstract: Systems and methods are disclosed for lookup-based convolutional neural networks. For example, methods may include applying a convolutional neural network to image data based on an image to obtain an output, in which a layer of the convolutional network includes filters with weights that are stored as a dictionary (D) of channel weight vectors, a respective lookup index tensor (I) that indexes the dictionary, and a respective lookup coefficient tensor (C), and in which applying the convolutional neural network includes: convolving the channel weight vectors of the dictionary (D) with an input tensor based on the image to obtain an input dictionary (S), and combining entries of the input dictionary (S) that are indexed with indices from the respective lookup index tensor (I) and multiplied with corresponding coefficients from the respective lookup coefficient tensor (C); and storing, displaying, or transmitting data based on the output of the convolutional neural network.

公开(公告)号：US11907823B2

公开(公告)日：2024-02-20

申请号：US17860031

申请日：2022-07-07

Applicant: Apple Inc.

Inventor： Saman Naderiparizi ,  Mohammad Rastegari ,  Sayyed Karen Khatamifard

IPC: G06N3/02 ,  G06F3/06 ,  G06N3/045 ,  G06N3/063

CPC classification number: G06N3/02 ,  G06F3/0604 ,  G06F3/0676 ,  G06F3/0677 ,  G06N3/045 ,  G06N3/063

Abstract: In one embodiment, a computing device includes an input sensor providing an input data; a programmable logic device (PLD) implementing a convolutional neural network (CNN), wherein: each compute block of the PLD corresponds to one of a multiple of convolutional layers of the CNN, each compute block of the PLD is placed in proximity to at least two memory blocks, a first one of the memory blocks serves as a buffer for the corresponding layer of the CNN, and a second one of the memory blocks stores model-specific parameters for the corresponding layer of the CNN.

公开(公告)号：US11651192B2

公开(公告)日：2023-05-16

申请号：US16788261

申请日：2020-02-11

Applicant: Apple Inc.

Inventor： James C. Gabriel ,  Mohammad Rastegari ,  Hessam Bagherinezhad ,  Saman Naderiparizi ,  Anish Prabhu ,  Sophie Lebrecht ,  Jonathan Gelsey ,  Sayyed Karen Khatamifard ,  Andrew L. Chronister ,  David Bakin ,  Andrew Z. Luo

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/08

Abstract: Systems and processes for training and compressing a convolutional neural network model include the use of quantization and layer fusion. Quantized training data is passed through a convolutional layer of a neural network model to generate convolutional results during a first iteration of training the neural network model. The convolutional results are passed through a batch normalization layer of the neural network model to update normalization parameters of the batch normalization layer. The convolutional layer is fused with the batch normalization layer to generate a first fused layer and the fused parameters of the fused layer are quantized. The quantized training data is passed through the fused layer using the quantized fused parameters to generate output data, which may be quantized for a subsequent layer in the training iteration.

公开(公告)号：US12079727B2

公开(公告)日：2024-09-03

申请号：US16892192

申请日：2020-06-03

Applicant: APPLE INC.

Inventor： Ali Farhadi ,  Mohammad Rastegari ,  Keivan Alizadeh Vahid

IPC: G06N3/084 ,  G06F17/14 ,  G06N3/02 ,  G06N3/04 ,  G06N3/048 ,  G06N3/082

CPC classification number: G06N3/084 ,  G06F17/142 ,  G06N3/02 ,  G06N3/04 ,  G06N3/048 ,  G06N3/082

Abstract: Input data having multiple channels may be received and passed through a convolutional neural network model to generate output data. Passing the input data through the convolutional neural network model may include passing the input data through a depth-wise convolutional layer configured to perform a convolution on the input data for each channel of the input data to generate first data. The first data is passed from the depth-wise convolutional layer through a butterfly transform layer comprising multiple sub-layers configured to perform a linear transformation of the first data to fuse the channels of the first data and generate second data, wherein the output data is based on the generated second data. The output data may be provided for further processing on a computing device.

公开(公告)号：US11657124B2

公开(公告)日：2023-05-23

申请号：US16215540

申请日：2018-12-10

Applicant: Apple Inc.

Inventor： Peter Zatloukal ,  Matthew Weaver ,  Alexander Kirchhoff ,  Dmitry Belenko ,  Ali Farhadi ,  Mohammad Rastegari ,  Andrew Luke Chronister ,  Keith Patrick Wyss ,  Chenfan Sun

IPC: G06F21/10 ,  G06N3/08 ,  G06N3/10 ,  H04L9/30 ,  H04L9/08 ,  G06F21/12

CPC classification number: G06F21/105 ,  G06F21/12 ,  G06N3/08 ,  G06N3/10 ,  H04L9/0891 ,  H04L9/30 ,  G06F2221/0755

Abstract: In one embodiment, a method includes receiving a user request from a client device associated with a user, accessing an instructional file comprising one or more binary inference engines and one or more encrypted model data corresponding to the one or more binary inference engines, respectively, selecting a binary inference engine from the one or more binary inference engines in the accessed instructional file based on the user request, sending a validation request for a permission to execute the binary inference engine to a licensing server, receiving the permission from the licensing server, decrypting the encrypted model data corresponding to the binary inference engine by a decryption key, executing the binary inference engine based on the user request and the decrypted model data, and sending one or more execution results responsive to the execution of the binary inference engine to the client device.