公开(公告)号：US09872276B2

公开(公告)日：2018-01-16

申请号：US14594562

申请日：2015-01-12

Applicant: Google Inc.

Inventor： Jean-Philippe Cormier ,  Guillaume Desjardins

IPC: H04W72/00 ,  H04W72/04 ,  H04W72/12 ,  H04L12/18 ,  H04W8/24 ,  H04M1/725

CPC classification number: H04W72/005 ,  H04L12/1881 ,  H04L12/189 ,  H04M1/72525 ,  H04W8/245

Abstract: A computing device may schedule transmission of software packages on a broadcast/multicast downlink channel. The schedule may also include media transmissions on the channel, and the software package transmissions may be scheduled for times when the media transmissions are using less than or equal to a threshold capacity level of the channel. A software update request may be received from a wireless computing device. Possibly in response to receiving the software update request, a particular software package related to the wireless computing device may be determined. The particular software package may be scheduled to begin transmission on the channel at a particular time. At least an identifier of the channel and the particular time may be transmitted to the wireless computing device.

公开(公告)号：US20160358073A1

公开(公告)日：2016-12-08

申请号：US15174020

申请日：2016-06-06

Applicant: Google Inc.

Inventor： Guillaume Desjardins ,  Karen Simonyan ,  Koray Kavukcuoglu ,  Razvan Pascanu

IPC: G06N3/08 ,  G06N99/00 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06N3/084 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a whitened neural network layer. One of the methods includes receiving an input activation generated by a layer before the whitened neural network layer in the sequence; processing the received activation in accordance with a set of whitening parameters to generate a whitened activation; processing the whitened activation in accordance with a set of layer parameters to generate an output activation; and providing the output activation as input to a neural network layer after the whitened neural network layer in the sequence.

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，用于使用包含白化神经网络层的神经网络系统处理输入。 其中一种方法包括在序列中接收由白化神经网络层之前的层产生的输入激活; 根据一组增白参数来处理接收到的激活以产生白化激活; 根据一组层参数处理白化激活以产生输出激活; 并且在序列中的白化神经网络层之后，将输出激活提供给神经网络层的输入。

公开(公告)号：US20160205662A1

公开(公告)日：2016-07-14

申请号：US14594562

申请日：2015-01-12

Applicant: GOOGLE INC.

Inventor： Jean-Philippe Cormier ,  Guillaume Desjardins

IPC: H04W72/00 ,  H04L12/18 ,  H04W72/04 ,  H04W72/12

CPC classification number: H04W72/005 ,  H04L12/1881 ,  H04L12/189 ,  H04M1/72525 ,  H04W8/245

Abstract: A computing device may schedule transmission of software packages on a broadcast/multicast downlink channel. The schedule may also include media transmissions on the channel, and the software package transmissions may be scheduled for times when the media transmissions are using less than or equal to a threshold capacity level of the channel. A software update request may be received from a wireless computing device. Possibly in response to receiving the software update request, a particular software package related to the wireless computing device may be determined. The particular software package may be scheduled to begin transmission on the channel at a particular time. At least an identifier of the channel and the particular time may be transmitted to the wireless computing device.

Abstract translation: 计算设备可以调度广播/多播下行链路信道上的软件包的传输。 调度还可以包括信道上的媒体传输，并且可以在媒体传输使用小于或等于信道的阈值容量级别的时间来调度软件包传输。 可以从无线计算设备接收软件更新请求。 可能响应于接收到软件更新请求，可以确定与无线计算设备相关的特定软件包。 特定软件包可以被调度为在特定时间开始在信道上传输。 至少信道的标识符和特定时间可以被发送到无线计算设备。

公开(公告)号：US20170337464A1

公开(公告)日：2017-11-23

申请号：US15396319

申请日：2016-12-30

Applicant: Google Inc.

Inventor： Neil Charles Rabinowitz ,  Guillaume Desjardins ,  Andrei-Alexandru Rusu ,  Koray Kavukcuoglu ,  Raia Thais Hadsell ,  Razvan Pascanu ,  James Kirkpatrick ,  Hubert Josef Soyer

IPC: G06N3/04 ,  G06N3/08 ,  G06F17/16

CPC classification number: G06F17/16 ,  G06N3/0454

Abstract: Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.