公开(公告)号：US20220366255A1

公开(公告)日：2022-11-17

申请号：US17874573

申请日：2022-07-27

Applicant: Google LLC

Inventor： Jonathan Ross ,  Norman Paul Jouppi ,  Andrew Everett Phelps ,  Reginald Clifford Young ,  Thomas Norrie ,  Gregory Michael Thorson ,  Dan Luu

IPC: G06N3/08 ,  G06F15/80 ,  G06N3/063 ,  G06N5/04

Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.

公开(公告)号：US20220138577A1

公开(公告)日：2022-05-05

申请号：US17575799

申请日：2022-01-14

Applicant: Google LLC

Inventor： Reginald Clifford Young

IPC: G06N3/08 ,  G06N3/063 ,  G06N5/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a respective neural network output for each of a plurality of inputs, the method comprising, for each of the neural network layers: receiving a plurality of inputs to be processed at the neural network layer; forming one or more batches of inputs from the plurality of inputs, each batch having a number of inputs up to the respective batch size for the neural network layer; selecting a number of the one or more batches of inputs to process, where a count of the inputs in the number of the one or more batches is greater than or equal to the respective associated batch size of a subsequent layer in the sequence; and processing the number of the one or more batches of inputs to generate the respective neural network layer output.

公开(公告)号：US20210224654A1

公开(公告)日：2021-07-22

申请号：US17226256

申请日：2021-04-09

Applicant: Google LLC

Inventor： Reginald Clifford Young

IPC: G06N3/08 ,  G06N3/063 ,  G06N5/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a respective neural network output for each of a plurality of inputs, the method comprising, for each of the neural network layers: receiving a plurality of inputs to be processed at the neural network layer; forming one or more batches of inputs from the plurality of inputs, each batch having a number of inputs up to the respective batch size for the neural network layer; selecting a number of the one or more batches of inputs to process, where a count of the inputs in the number of the one or more batches is greater than or equal to the respective associated batch size of a subsequent layer in the sequence; and processing the number of the one or more batches of inputs to generate the respective neural network layer output.

公开(公告)号：US20210125029A1

公开(公告)日：2021-04-29

申请号：US17060420

申请日：2020-10-01

Applicant: Google LLC

Inventor： Reginald Clifford Young ,  Jonathan Ross

IPC: G06N3/04 ,  G06N3/02 ,  G06N3/063 ,  G06F17/16

Abstract: Methods, systems, and apparatus for efficiently performing a computation of a convolutional neural network layer. One of the methods includes transforming a X by Y by Z input tensor into a X′ by Y′ by Z′ input tensor, wherein X′ is smaller than or equal to X, Y′ is smaller than or equal to Y, and Z′ is larger than or equal to Z; obtaining one or more modified weight matrices, wherein the modified weight matrices operate on the X′ by Y′ by Z′ input tensor to generate a U′ by V′ by W′ output tensor, and the U′ by V′ by W′ output tensor is a transformed U by V by W output tensor; and processing the X′ by Y′ by Z′ input tensor using the modified weight matrices to generate the U′ by V′ by W′ output tensor.

公开(公告)号：US20210019618A1

公开(公告)日：2021-01-21

申请号：US16915161

申请日：2020-06-29

Applicant: Google LLC

Inventor： Jonathan Ross ,  Norman Paul Jouppi ,  Andrew Everett Phelps ,  Reginald Clifford Young ,  Thomas Norrie ,  Gregory Michael Thorson ,  Dan Luu

IPC: G06N3/08 ,  G06F15/80 ,  G06N3/063 ,  G06N5/04

Abstract: A circuit for performing neural network computations for a neural network comprising a plurality of neural network layers, the circuit comprising: a matrix computation unit configured to, for each of the plurality of neural network layers: receive a plurality of weight inputs and a plurality of activation inputs for the neural network layer, and generate a plurality of accumulated values based on the plurality of weight inputs and the plurality of activation inputs; and a vector computation unit communicatively coupled to the matrix computation unit and configured to, for each of the plurality of neural network layers: apply an activation function to each accumulated value generated by the matrix computation unit to generate a plurality of activated values for the neural network layer.

公开(公告)号：US20190354863A1

公开(公告)日：2019-11-21

申请号：US16531703

申请日：2019-08-05

Applicant: Google LLC

Inventor： Reginald Clifford Young ,  William John Gulland

IPC: G06N3/08 ,  G06N3/063 ,  G06N5/04 ,  G06N3/04

Abstract: Methods and systems for receiving a request to implement a neural network comprising an average pooling layer on a hardware circuit, and in response, generating instructions that when executed by the hardware circuit, cause the hardware circuit to, during processing of a network input by the neural network, generate a layer output tensor that is equivalent to an output of the average pooling neural network layer by performing a convolution of an input tensor to the average pooling neural network layer and a kernel with a size equal to a window of the average pooling neural network layer and composed of elements that are each an identity matrix to generate a first tensor, and performing operations to cause each element of the first tensor to be divided by a number of elements in the window of the average pooling neural network layer to generate an initial output tensor.

公开(公告)号：US10373049B2

公开(公告)日：2019-08-06

申请号：US15385642

申请日：2016-12-20

Applicant: Google LLC

Inventor： Reginald Clifford Young

IPC: G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00 ,  G06N3/04 ,  G06N3/063 ,  G06N7/00

Abstract: Systems, methods, and apparatus, including computer programs encoded on a computer storage medium for processing a network input through a neural network having one or more initial neural network layers followed by a softmax output layer. In one aspect, the methods include obtaining a layer output generated by the one or more initial neural network layers and processing the layer output through the softmax output layer to generate a neural network output. Processing the layer output through the softmax output layer includes determining, for each possible output value, a number of occurrences in the layer output values; for each possible output value occurring in the layer output values, determining a respective exponentiation measure; determining a normalization factor for the layer output by combining the exponentiation measures in accordance with the number of occurrences of the possible output values; and determining, for each of layer output values, a softmax probability value.

公开(公告)号：US10032110B2

公开(公告)日：2018-07-24

申请号：US15377196

申请日：2016-12-13

Applicant: Google LLC

Inventor： Reginald Clifford Young ,  William John Gulland

IPC: G06N3/06 ,  G06N3/063 ,  G06N3/04 ,  G06F7/483 ,  G06F7/52 ,  G06F17/16

CPC classification number: G06F17/16 ,  G06F7/483 ,  G06F7/52 ,  G06F7/5443 ,  G06F2207/4824 ,  G06N3/04 ,  G06N3/063

Abstract: Methods and systems for receiving a request to implement a neural network comprising an average pooling layer on a hardware circuit, and in response, generating instructions that when executed by the hardware circuit, cause the hardware circuit to, during processing of a network input by the neural network, generate a layer output tensor that is equivalent to an output of the average pooling neural network layer by performing a convolution of an input tensor to the average pooling neural network layer and a kernel with a size equal to a window of the average pooling neural network layer and composed of elements that are each an identity matrix to generate a first tensor, and performing operations to cause each element of the first tensor to be divided by a number of elements in the window of the average pooling neural network layer to generate an initial output tensor.

公开(公告)号：US10007876B1

公开(公告)日：2018-06-26

申请号：US15476809

申请日：2017-03-31

Applicant: Google LLC

Inventor： Reginald Clifford Young

IPC: G06N3/04

Abstract: Systems, methods, and apparatus, including computer programs encoded on a computer storage medium for processing a network input through a neural network having one or more initial neural network layers followed by a softmax output layer. In one aspect, the methods include obtaining a layer output generated by the one or more initial neural network layers and processing the layer output through the softmax output layer to generate a neural network output. Processing the layer output through the softmax output layer includes determining, for each possible output value, a number of occurrences in the layer output values; for each possible output value occurring in the layer output values, determining a respective exponentiation measure; determining a normalization factor for the layer output by combining the exponentiation measures in accordance with the number of occurrences of the possible output values; and determining, for each of layer output values, a softmax probability value.

公开(公告)号：US09940573B2

公开(公告)日：2018-04-10

申请号：US15473027

申请日：2017-03-29

Applicant: Google LLC

Inventor： Reginald Clifford Young ,  Jonathan Ross

IPC: G06N3/04 ,  G06F17/16

CPC classification number: G06N3/04 ,  G06F17/16 ,  G06N3/02 ,  G06N3/063

Abstract: Methods, systems, and apparatus for efficiently performing a computation of a convolutional neural network layer. One of the methods includes transforming a X by Y by Z input tensor into a X′ by Y′ by Z′ input tensor, wherein X′ is smaller than or equal to X, Y′ is smaller than or equal to Y, and Z′ is larger than or equal to Z; obtaining one or more modified weight matrices, wherein the modified weight matrices operate on the X′ by Y′ by Z′ input tensor to generate a U′ by V′ by W′ output tensor, and the U′ by V′ by W′ output tensor comprises a transformed U by V by W output tensor, wherein U′ is smaller than or equal to U, V′ is smaller than or equal to V, and W′ is larger than or equal to W; and processing the X′ by Y′ by Z′ input tensor using the modified weight matrices to generate the U′ by V′ by W′ output tensor, wherein the U′ by V′ by W′ output tensor comprises the U by V by W output tensor.