公开(公告)号：US20170323201A1

公开(公告)日：2017-11-09

申请号：US15396331

申请日：2016-12-30

Applicant: Google Inc.

Inventor： Ilya Sutskever ,  Ivo Danihelka ,  Alexander Benjamin Graves ,  Gregory Duncan Wayne ,  Wojciech Zaremba

IPC: G06N3/08 ,  G06F3/06

CPC classification number: G06N3/08 ,  G06F3/0604 ,  G06F3/0653 ,  G06F3/0673 ,  G06N3/0445 ,  G06N3/063

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory using reinforcement learning. One of the methods includes providing an output derived from the system output portion of the neural network output as a system output in the sequence of system outputs; selecting a memory access process from a predetermined set of memory access processes for accessing the external memory from the reinforcement learning portion of the neural network output; writing and reading data from locations in the external memory in accordance with the selected memory access process using the differentiable portion of the neural network output; and combining the data read from the external memory with a next system input in the sequence of system inputs to generate a next neural network input in the sequence of neural network inputs.

公开(公告)号：US20170228633A1

公开(公告)日：2017-08-10

申请号：US15424708

申请日：2017-02-03

Applicant: Google Inc.

Inventor： Ivo Danihelka ,  Danilo Jimenez Rezende ,  Shakir Mohamed

IPC: G06N3/04 ,  G06K9/66 ,  G06K9/62 ,  G06N3/08

CPC classification number: G06N3/0445 ,  G06K9/6257 ,  G06K9/66 ,  G06N3/0472 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a neural network system. In one aspect, a neural network system includes a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the latent variables to update a hidden state of the recurrent neural network; and a generative subsystem that is configured to, for each time step, generate the set of latent variables for the time step and provide the set of latent variables as input to the recurrent neural network; update a hidden canvas using the updated hidden state of the recurrent neural network; and, for a last time step, generate an output image using the updated hidden canvas for the last time step.

公开(公告)号：US20160232440A1

公开(公告)日：2016-08-11

申请号：US15016160

申请日：2016-02-04

Applicant: Google Inc.

Inventor： Karol Gregor ,  Ivo Danihelka

IPC: G06N3/04

CPC classification number: G06N3/04 ,  G06N3/0445 ,  G06N3/0454 ,  G10L13/02 ,  G10L25/30

Abstract: Methods, and systems, including computer programs encoded on computer storage media for generating data items. A method includes reading a glimpse from a data item using a decoder hidden state vector of a decoder for a preceding time step, providing, as input to a encoder, the glimpse and decoder hidden state vector for the preceding time step for processing, receiving, as output from the encoder, a generated encoder hidden state vector for the time step, generating a decoder input from the generated encoder hidden state vector, providing the decoder input to the decoder for processing, receiving, as output from the decoder, a generated a decoder hidden state vector for the time step, generating a neural network output update from the decoder hidden state vector for the time step, and combining the neural network output update with a current neural network output to generate an updated neural network output.

Abstract translation: 方法和系统，包括在用于生成数据项的计算机存储介质上编码的计算机程序。 一种方法包括使用解码器的解码器隐藏状态向量从数据项中读取前一时间步长，向编码器提供前一时间步长的瞥见和解码器隐藏状态向量的输入，用于处理，接收， 作为编码器的输出，生成用于时间步长的编码器隐藏状态向量，从所生成的编码器隐藏状态矢量生成解码器输入，向解码器提供解码器输入，以处理，接收来自解码器的输出，生成的 用于时间步长的解码器隐藏状态向量，从时间步骤的解码器隐藏状态向量生成神经网络输出更新，并且将神经网络输出更新与当前神经网络输出组合以生成更新的神经网络输出。

公开(公告)号：US20170228638A1

公开(公告)日：2017-08-10

申请号：US15424685

申请日：2017-02-03

Applicant: Google Inc.

Inventor： Ivo Danihelka ,  Gregory Duncan Wayne ,  Fu-min Wang ,  Edward Thomas Grefenstette ,  Jack William Rae ,  Alexander Benjamin Graves ,  Timothy Paul Lillicrap ,  Timothy James Alexander Harley ,  Jonathan James Hunt

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

CPC classification number: G06N3/063 ,  G06N3/0445 ,  G06N3/082

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a sparse memory access subsystem that is configured to perform operations comprising generating a sparse set of reading weights that includes a respective reading weight for each of the plurality of locations in the external memory using the read key, reading data from the plurality of locations in the external memory in accordance with the sparse set of reading weights, generating a set of writing weights that includes a respective writing weight for each of the plurality of locations in the external memory, and writing the write vector to the plurality of locations in the external memory in accordance with the writing weights.

公开(公告)号：US20170228637A1

公开(公告)日：2017-08-10

申请号：US15396289

申请日：2016-12-30

Applicant: Google Inc.

Inventor： Adam Anthony Santoro ,  Daniel Pieter Wierstra ,  Timothy Paul Lillicrap ,  Sergey Bartunov ,  Ivo Danihelka

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

CPC classification number: G06N3/063 ,  G06F12/123 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a controller neural network that includes a Least Recently Used Access (LRUA) subsystem configured to: maintain a respective usage weight for each of a plurality of locations in the external memory, and for each of the plurality of time steps: generate a respective reading weight for each location using a read key, read data from the locations in accordance with the reading weights, generate a respective writing weight for each of the locations from a respective reading weight from a preceding time step and the respective usage weight for the location, write a write vector to the locations in accordance with the writing weights, and update the respective usage weight from the respective reading weight and the respective writing weight.

公开(公告)号：US20170169332A1

公开(公告)日：2017-06-15

申请号：US15374974

申请日：2016-12-09

Applicant: Google Inc.

Inventor： Alexander Benjamin Graves ,  Ivo Danihelka ,  Timothy James Alexander Harley ,  Malcolm Kevin Campbell Reynolds ,  Gregory Duncan Wayne

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a memory interface subsystem that is configured to perform operations comprising determining a respective content-based weight for each of a plurality of locations in an external memory; determining a respective allocation weight for each of the plurality of locations in the external memory; determining a respective final writing weight for each of the plurality of locations in the external memory from the respective content-based weight for the location and the respective allocation weight for the location; and writing data defined by the write vector to the external memory in accordance with the final writing weights.

公开(公告)号：US20160189027A1

公开(公告)日：2016-06-30

申请号：US14977201

申请日：2015-12-21

Applicant: Google Inc.

Inventor： Alexander Benjamin Graves ,  Ivo Danihelka ,  Gregory Duncan Wayne

IPC: G06N3/08 ,  G06N3/063

CPC classification number: G06N3/08 ,  G06N3/0454 ,  G06N3/063

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks to generate additional outputs. One of the systems includes a neural network and a sequence processing subsystem, wherein the sequence processing subsystem is configured to perform operations comprising, for each of the system inputs in a sequence of system inputs: receiving the system input; generating an initial neural network input from the system input; causing the neural network to process the initial neural network input to generate an initial neural network output for the system input; and determining, from a first portion of the initial neural network output for the system input, whether or not to cause the neural network to generate one or more additional neural network outputs for the system input.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于增加神经网络以产生附加输出。 系统中的一个包括神经网络和序列处理子系统，其中序列处理子系统被配置为对系统输入中的每一个执行包括系统输入序列的操作：接收系统输入; 从系统输入产生初始神经网络输入; 使神经网络处理初始神经网络输入，为系统输入生成初始神经网络输出; 以及从所述系统输入的所述初始神经网络输出的第一部分确定是否使所述神经网络生成用于所述系统输入的一个或多个附加神经网络输出。

公开(公告)号：US20160117586A1

公开(公告)日：2016-04-28

申请号：US14885086

申请日：2015-10-16

Applicant: Google Inc.

Inventor： Alexander Benjamin Graves ,  Ivo Danihelka ,  Gregory Duncan Wayne

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the methods includes providing an output derived from a first portion of a neural network output as a system output; determining one or more sets of writing weights for each of a plurality of locations in an external memory; writing data defined by a third portion of the neural network output to the external memory in accordance with the sets of writing weights; determining one or more sets of reading weights for each of the plurality of locations in the external memory from a fourth portion of the neural network output; reading data from the external memory in accordance with the sets of reading weights; and combining the data read from the external memory with a next system input to generate the next neural network input.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于利用外部存储器增强神经网络。 一种方法包括提供从神经网络输出的第一部分导出的输出作为系统输出; 为外部存储器中的多个位置中的每一个确定一组或多组写入权重; 根据所述书写权重集将所述神经网络输出的第三部分定义的数据写入所述外部存储器; 从所述神经网络输出的第四部分确定所述外部存储器中的所述多个位置中的每一个的一组或多组读取权重; 根据阅读权重集从外部存储器读取数据; 以及将从外部存储器读取的数据与下一个系统输入组合以生成下一个神经网络输入。

公开(公告)号：US20170228642A1

公开(公告)日：2017-08-10

申请号：US15395553

申请日：2016-12-30

Applicant: Google Inc.

Inventor： Ivo Danihelka ,  Nal Emmerich Kalchbrenner ,  Gregory Duncan Wayne ,  Benigno Uría-Martínez ,  Alexander Benjamin Graves

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06N3/0445

Abstract: Systems, methods, and apparatus, including computer programs encoded on a computer storage medium, related to associative long short-term memory (LSTM) neural network layers configured to maintain N copies of an internal state for the associative LSTM layer, N being an integer greater than one. In one aspect, a system includes a recurrent neural network including an associative LSTM layer, wherein the associative LSTM layer is configured to, for each time step, receive a layer input, update each of the N copies of the internal state using the layer input for the time step and a layer output generated by the associative LSTM layer for a preceding time step, and generate a layer output for the time step using the N updated copies of the internal state.