-
公开(公告)号：US20160358071A1
公开(公告)日：2016-12-08
申请号：US15172068
申请日：2016-06-02
Applicant: Google Inc.
Inventor： Edward Thomas Grefenstette , Karl Moritz Hermann , Mustafa Suleyman , Philip Blunsom
IPC: G06N3/08
CPC classification number: G06N3/08 , G06N3/0445 , G06N3/063 , 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 methods includes providing an output derived from the neural network output for the time step as a system output for the time step; maintaining a current state of the external memory; determining, from the neural network output for the time step, memory state parameters for the time step; updating the current state of the external memory using the memory state parameters for the time step; reading data from the external memory in accordance with the updated state of the external memory; and combining the data read from the external memory with a system input for the next time step to generate the neural network input for the next time step.
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。 其中一种方法包括提供从时间步长的神经网络输出得到的输出作为时间步长的系统输出; 保持外部存储器的当前状态; 从时间步长的神经网络输出确定时间步长的存储器状态参数; 使用时间步长的存储器状态参数来更新外部存储器的当前状态; 根据外部存储器的更新状态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用于下一时间步长的系统输入组合以生成下一个时间步长的神经网络输入。
-
公开(公告)号：US20160232445A1
公开(公告)日：2016-08-11
申请号：US15016173
申请日：2016-02-04
Applicant: Google Inc.
Inventor： Praveen Deepak Srinivasan , Rory Fearon , Cagdas Alcicek , Arun Sarath Nair , Samuel Blackwell , Vedavyas Panneershelvam , Alessandro De Maria , Volodymyr Mnih , Koray Kavukcuoglu , David Silver , Mustafa Suleyman
CPC classification number: G06N3/08 , G06N3/0454 , G06N3/0472
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributed training of reinforcement learning systems. One of the methods includes receiving, by a learner, current values of the parameters of the Q network from a parameter server, wherein each learner maintains a respective learner Q network replica and a respective target Q network replica; updating, by the learner, the parameters of the learner Q network replica maintained by the learner using the current values; selecting, by the learner, an experience tuple from a respective replay memory; computing, by the learner, a gradient from the experience tuple using the learner Q network replica maintained by the learner and the target Q network replica maintained by the learner; and providing, by the learner, the computed gradient to the parameter server.
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，用于强化学习系统的分布式训练。 其中一种方法包括从学习者接收来自参数服务器的Q网络参数的当前值，其中每个学习者维护相应的学习者Q网络副本和相应的目标Q网络副本; 由学习者更新由学习者使用当前值维护的学习者Q网络副本的参数; 由学习者选择来自相应回放记忆的经验元组; 由学习者使用由学习者维护的学习者Q网络副本和学习者维护的目标Q网络副本的经验元组进行计算; 并且由学习者将计算的梯度提供给参数服务器。
-
Patent Agency Ranking
公开(公告)号：US08873838B2
公开(公告)日：2014-10-28
申请号：US13804257
申请日：2013-03-14
Applicant: Google Inc.
Inventor： Mustafa Suleyman , Benjamin Kenneth Coppin , Marek Barwinski , Arun Nair , Andrei-Alexandru Rusu , Chia-Yueh Carlton Chu
IPC: G06K9/62
CPC classification number: G06K9/6217 , G06K9/00362 , G06K9/4628 , G06N3/0454 , G06N3/084
Abstract: The present invention relates to a method and system for characterizing an image. The characterization may then be used to conduct a search for similar images, for example using a learning system trained using previously characterized images. A face may be identified within the image and a subsection extracted from said image which does not contain said face. At least one fixed size patch is taken from said extracted subsection; and input into said learning network to characterize said image.
Abstract translation: 本发明涉及一种用于表征图像的方法和系统。 然后，可以使用表征来进行类似图像的搜索，例如使用使用先前描述的图像训练的学习系统。 可以在图像内识别面部和从不包含所述脸部的所述图像提取的子部分。 从所述提取的子段中取出至少一个固定大小的补丁; 并输入到所述学习网络中以表征所述图像。
-
公开(公告)号：US20180018580A1
公开(公告)日：2018-01-18
申请号：US15212037
申请日：2016-07-15
Applicant: Google Inc.
Inventor： Benjamin Kenneth Coppin , Mustafa Suleyman , Thomas Chadwick Walters , Timothy Mann , Chia-Yueh Carlton Chu , Martin Szummer , Luis Carlos Cobo Rus , Jean-Francois Crespo
CPC classification number: G06N20/00 , G06F16/24578 , G06F16/9535 , G06N3/0445 , G06N3/084 , G06N7/005
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.
-
公开(公告)号：US20160358072A1
公开(公告)日：2016-12-08
申请号：US15172074
申请日：2016-06-02
Applicant: Google Inc.
Inventor： Karl Moritz Hermann , Tomas Kocisky , Edward Thomas Grefenstette , Lasse Espeholt , William Thomas Kay , Mustafa Suleyman , Philip Blunsom
IPC: G06N3/08 , G06F3/0484
CPC classification number: G06N3/08 , G06F3/0484 , G06N3/0427 , G06N3/0445 , G06N3/0454
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting answers to questions about documents. One of the methods includes receiving a document comprising a plurality of document tokens; receiving a question associated with the document, the question comprising a plurality of question tokens; processing the document tokens and the question tokens using a reader neural network to generate a joint numeric representation of the document and the question; and selecting, from the plurality of document tokens, an answer to the question using the joint numeric representation of the document and the question.
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，用于选择关于文件的问题的答案。 其中一种方法包括接收包括多个文档令牌的文档; 接收与文档相关联的问题，该问题包括多个问题令牌; 使用读取器神经网络处理文档令牌和问题令牌以生成文档和问题的联合数字表示; 以及使用所述文档和所述问题的联合数字表示从所述多个文档令牌中选择所述问题的答案。
-
公开(公告)号：US08971669B2
公开(公告)日：2015-03-03
申请号：US14155434
申请日：2014-01-15
Applicant: Google Inc.
Inventor： Benjamin Kenneth Coppin , Mustafa Suleyman , Arun Nair
CPC classification number: G06F17/30262 , G06K9/00 , G06K9/46 , G06K2009/4666
Abstract: A method for processing an image to generate a signature which is characteristic of a pattern within said image. The method comprising receiving an image; overlaying a window at multiple locations on said image to define a plurality of sub-images within said image, with each sub-image each having a plurality of pixels having a luminance level; determining a luminance value for each said sub-image, wherein said luminance value is derived from said luminance levels of said plurality of pixels; and combining said luminance values for each of said sub-images to form said signature. Said combining is such that said signature is independent of the location of each sub-image. A method of creating a database of images using said method of generating signatures is also described.
Abstract translation: 一种用于处理图像以生成作为所述图像内的图案的特征的签名的方法。 该方法包括接收图像; 在所述图像上的多个位置处覆盖窗口以在所述图像内定义多个子图像，每个子图像各自具有具有亮度级的多个像素; 确定每个所述子图像的亮度值，其中所述亮度值从所述多个像素的所述亮度级导出; 以及将每个所述子图像的所述亮度值组合以形成所述签名。 所述组合使得所述签名独立于每个子图像的位置。 还描述了使用所述生成签名的方法来创建图像数据库的方法。
-
公开(公告)号：US20140270488A1
公开(公告)日：2014-09-18
申请号：US13804257
申请日：2013-03-14
Applicant: Google Inc.
Inventor： Mustafa Suleyman , Benjamin Kenneth Coppin , Marek Barwinski , Arun Nair , Andrei-Alexandru Rusu , Chia-Yueh Carlton Chu
IPC: G06K9/62
CPC classification number: G06K9/6217 , G06K9/00362 , G06K9/4628 , G06N3/0454 , G06N3/084
Abstract: The present invention relates to a method and system for characterizing an image. The characterization may then be used to conduct a search for similar images, for example using a learning system trained using previously characterized images. A face may be identified within the image and a subsection extracted from said image which does not contain said face. At least one fixed size patch is taken from said extracted subsection; and input into said learning network to characterize said image.
Abstract translation: 本发明涉及一种用于表征图像的方法和系统。 然后，可以使用表征来进行类似图像的搜索，例如使用使用先前描述的图像训练的学习系统。 可以在图像内识别面部和从不包含所述脸部的所述图像提取的子部分。 从所述提取的子段中取出至少一个固定大小的补丁; 并输入到所述学习网络中以表征所述图像。
-
-
-
-
-
-
Search Results
7
records
(took 0.012 seconds)
