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：US20170230675A1

公开(公告)日：2017-08-10

申请号：US15396332

申请日：2016-12-30

Applicant: Google Inc.

Inventor： Daniel Pieter Wierstra ,  Karol Gregor ,  Frederic Olivier Besse

IPC: H04N19/30 ,  G06N3/08 ,  H04N19/44 ,  G06N3/04

CPC classification number: H04N19/30 ,  G06N3/0454 ,  G06N3/0472 ,  G06N3/08 ,  G06T9/002 ,  H04N19/44

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for compressing images using neural networks. One of the methods includes receiving an image; processing the image using an encoder neural network, wherein the encoder neural network is configured to receive the image and to process the image to generate an output defining values of a first number of latent variables that each represent a feature of the image; generating a compressed representation of the image using the output defining the values of the first number of latent variables; and providing the compressed representation of the image for use in generating a reconstruction of the image.

公开(公告)号：US20170024643A1

公开(公告)日：2017-01-26

申请号：US15217758

申请日：2016-07-22

Applicant: Google Inc.

Inventor： Timothy Paul Lillicrap ,  Jonathan James Hunt ,  Alexander Pritzel ,  Nicolas Manfred Otto Heess ,  Tom Erez ,  Yuval Tassa ,  David Silver ,  Daniel Pieter Wierstra

IPC: G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an actor neural network used to select actions to be performed by an agent interacting with an environment. One of the methods includes obtaining a minibatch of experience tuples; and updating current values of the parameters of the actor neural network, comprising: for each experience tuple in the minibatch: processing the training observation and the training action in the experience tuple using a critic neural network to determine a neural network output for the experience tuple, and determining a target neural network output for the experience tuple; updating current values of the parameters of the critic neural network using errors between the target neural network outputs and the neural network outputs; and updating the current values of the parameters of the actor neural network using the critic neural network.

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，用于训练用于选择由与环境交互的代理执行的动作的动作者神经网络。 其中一种方法包括获取经验元组的小批量; 并且更新所述演员神经网络的参数的当前值，包括：对于所述迷你服务中的每个经验元组：使用批评神经网络来处理训练观察和经验元组中的训练动作以确定体验元组的神经网络输出 ，并且为所述体验元组确定目标神经网络输出; 使用目标神经网络输出与神经网络输出之间的误差来更新评价神经网络参数的当前值; 并使用批评神经网络更新演员神经网络的参数的当前值。