-
公开(公告)号：US20180032863A1
公开(公告)日：2018-02-01
申请号：US15280711
申请日：2016-09-29
Applicant: Google Inc.
Inventor： Thore Kurt Hartwig Graepel , Shih-Chieh Huang , David Silver , Arthur Clement Guez , Laurent Sifre , Ilya Sutskever , Christopher Maddison
CPC classification number: G06N3/08 , G05B13/027 , G06N3/04 , G06N3/0427 , G06N3/0454 , G16B40/00 , G16H50/20
Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media, for training a value neural network that is configured to receive an observation characterizing a state of an environment being interacted with by an agent and to process the observation in accordance with parameters of the value neural network to generate a value score. One of the systems performs operations that include training a supervised learning policy neural network; initializing initial values of parameters of a reinforcement learning policy neural network having a same architecture as the supervised learning policy network to the trained values of the parameters of the supervised learning policy neural network; training the reinforcement learning policy neural network on second training data; and training the value neural network to generate a value score for the state of the environment that represents a predicted long-term reward resulting from the environment being in the state.
-
公开(公告)号：US09811775B2
公开(公告)日：2017-11-07
申请号：US14030938
申请日：2013-09-18
Applicant: Google Inc.
Inventor： Alexander Krizhevsky , Ilya Sutskever , Geoffrey E. Hinton
CPC classification number: G06N3/04 , G06K9/4628 , G06K9/6256 , G06K9/66 , G06N3/0454 , G06N3/063 , G06N3/08 , G06T1/20
Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.
-
公开(公告)号：US20170140265A1
公开(公告)日：2017-05-18
申请号：US15349955
申请日：2016-11-11
Applicant: Google Inc.
Inventor： Quoc V. Le , Ilya Sutskever , Arvind Neelakantan
CPC classification number: G06N3/0445 , G06N3/08
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing operations using data from a data source. In one aspect, a method includes a neural network system including a controller neural network configured to: receive a controller input for a time step and process the controller input and a representation of a system input to generate: an operation score distribution that assigns a respective operation score to an operation and a data score distribution that assigns a respective data score in the data source. The neural network system can also include an operation subsystem configured to: perform operations to generate operation outputs, wherein at least one of the operations is performed on data in the data source, and combine the operation outputs in accordance with the operation score distribution and the data score distribution to generate a time step output for the time step.
-
公开(公告)号：US09406017B2
公开(公告)日：2016-08-02
申请号：US14015768
申请日：2013-08-30
Applicant: Google Inc.
Inventor： Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastva
CPC classification number: G06N3/084 , G06K9/4628 , G06N3/0454 , G06N3/0472 , G06N3/082
Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
Abstract translation: 用于训练神经网络的系统。 开关被连接到神经网络的至少一些层中的特征检测器。 对于每个训练情况，交换机根据预配置的概率随机选择性地禁用每个特征检测器。 然后对每个训练情况的权重进行归一化，以将神经网络应用于测试数据。
-
公开(公告)号：US20180032864A1
公开(公告)日：2018-02-01
申请号：US15280784
申请日：2016-09-29
Applicant: Google Inc.
Inventor： Thore Kurt Hartwig Graepel , Shih-Chieh Huang , David Silver , Arthur Clement Guez , Laurent Sifre , Ilya Sutskever , Christopher Maddison
CPC classification number: G06N3/08 , G06F16/9027 , G06N3/0427 , G06N3/0454 , G06N5/003 , G16B40/00 , G16H50/20
Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media, for training a value neural network that is configured to receive an observation characterizing a state of an environment being interacted with by an agent and to process the observation in accordance with parameters of the value neural network to generate a value score. One of the systems performs operations that include training a supervised learning policy neural network; initializing initial values of parameters of a reinforcement learning policy neural network having a same architecture as the supervised learning policy network to the trained values of the parameters of the supervised learning policy neural network; training the reinforcement learning policy neural network on second training data; and training the value neural network to generate a value score for the state of the environment that represents a predicted long-term reward resulting from the environment being in the state.
-
Patent Agency Ranking
公开(公告)号：US20160117316A1
公开(公告)日：2016-04-28
申请号：US14921925
申请日：2015-10-23
Applicant: Google Inc.
Inventor： Quoc V. Le , Minh-Thang Luong , Ilya Sutskever , Oriol Vinyals , Wojciech Zaremba
CPC classification number: G06F17/2881 , G06F7/023 , G06F7/10 , G06F17/2735 , G06F17/2818 , G06F17/2827 , G06N3/0445 , G06N3/0454 , G10L15/02 , G10L15/16
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for neural translation systems with rare word processing. One of the methods is a method training a neural network translation system to track the source in source sentences of unknown words in target sentences, in a source language and a target language, respectively and includes deriving alignment data from a parallel corpus, the alignment data identifying, in each pair of source and target language sentences in the parallel corpus, aligned source and target words; annotating the sentences in the parallel corpus according to the alignment data and a rare word model to generate a training dataset of paired source and target language sentences; and training a neural network translation model on the training dataset.
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，用于具有罕见文字处理的神经翻译系统。 其中一种方法是训练神经网络翻译系统，以分别在源语言和目标语言中跟踪目标语句中的未知单词的源语句中的源，并且包括从并行语料库导出对齐数据，对齐数据 在平行语料库中的每对源和目标语言句子中识别对齐的源词和目标词; 根据对齐数据和平行语料库中的句子注释罕见词模型，以生成配对的源语言和目标语言句子的训练数据集; 并在训练数据集上训练神经网络翻译模型。
-
公开(公告)号：US20140180989A1
公开(公告)日：2014-06-26
申请号：US14030938
申请日：2013-09-18
Applicant: Google Inc.
Inventor： Alexander Krizhevsky , Ilya Sutskever , Geoffrey E. Hinton
IPC: G06N3/04
CPC classification number: G06N3/04 , G06K9/4628 , G06K9/6256 , G06K9/66 , G06N3/0454 , G06N3/063 , G06N3/08 , G06T1/20
Abstract: A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.
Abstract translation: 提供并行卷积神经网络。 CNN由各自的处理节点上的多个卷积神经网络实现。 每个CNN具有多个层。 层的一个子集在处理节点之间互连，使得激活在节点之间向前馈送。 剩下的子集并不是互连的。
-
公开(公告)号：US20140180986A1
公开(公告)日：2014-06-26
申请号：US14015768
申请日：2013-08-30
Applicant: Google Inc.
Inventor： Geoffrey E. Hinton , Alexander Krizhevsky , Ilya Sutskever , Nitish Srivastva
IPC: G06N3/08
CPC classification number: G06N3/084 , G06K9/4628 , G06N3/0454 , G06N3/0472 , G06N3/082
Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.
Abstract translation: 用于训练神经网络的系统。 开关被连接到神经网络的至少一些层中的特征检测器。 对于每个训练情况，交换机根据预配置的概率随机选择性地禁用每个特征检测器。 然后对每个训练情况的权重进行归一化，以将神经网络应用于测试数据。
-
公开(公告)号：US20170140263A1
公开(公告)日：2017-05-18
申请号：US15349867
申请日：2016-11-11
Applicant: Google Inc.
Inventor： Lukasz Mieczyslaw Kaiser , Ilya Sutskever
CPC classification number: G06N3/0445 , G06F17/16 , G06N3/0454 , G06N3/08
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a convolutional gated recurrent neural network (CGRN). In one of the systems, the CGRN is configured to maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one, and for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates.
-
公开(公告)号：US09646244B2
公开(公告)日：2017-05-09
申请号：US15150091
申请日：2016-05-09
Applicant: Google Inc.
Inventor： Gregory Sean Corrado , Ilya Sutskever , Jeffrey Adgate Dean
CPC classification number: G06N3/0472 , G06F19/00 , G06N3/02 , G06N3/0427 , G06N3/0445 , G06N3/063 , G16H50/20
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting likelihoods of conditions being satisfied using recurrent neural networks. One of the systems is configured to process a temporal sequence comprising a respective input at each of a plurality of time steps and comprises: one or more recurrent neural network layers; one or more logistic regression nodes, wherein each of the logistic regression nodes corresponds to a respective condition from a predetermined set of conditions, and wherein each of the logistic regression nodes is configured to, for each of the plurality of time steps: receive the network internal state for the time step; and process the network internal state for the time step in accordance with current values of a set of parameters of the logistic regression node to generate a future condition score for the corresponding condition for the time step.
-
-
-
-
-
-
-
-
-
Search Results
26
records
(took 0.016 seconds)
