专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2020152267A1 LEARNING NON-DIFFERENTIABLE WEIGHTS OF NEURAL NETWORKS USING EVOLUTIONARY STRATEGIES 审中-公开
公开(公告)号：WO2020152267A1
公开(公告)日：2020-07-30
申请号：PCT/EP2020/051623
申请日：2020-01-23
申请人： DEEPMIND TECHNOLOGIES LIMITED , SCHAUL, Tom , ELSEN, Erich Konrad
发明人： SCHAUL, Tom , ELSEN, Erich Konrad , LENC, Karel , SIMONYAN, Karen
IPC分类号： G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. The neural network has a plurality of differentiable weights and a plurality of non-differentiable weights. One of the methods includes determining trained values of the plurality of differentiable weights and the non-differentiable weights by repeatedly performing operations that include determining an update to the current values of the plurality of differentiable weights using a machine learning gradient-based training technique and determining, using an evolution strategies (ES) technique, an update to the current values of a plurality of distribution parameters.

2. 发明申请

WO2020234476A1 LARGE SCALE GENERATIVE NEURAL NETWORK MODEL WITH INFERENCE FOR REPRESENTATION LEARNING USING ADVERSIAL TRAINING 审中-公开
公开(公告)号：WO2020234476A1
公开(公告)日：2020-11-26
申请号：PCT/EP2020/064340
申请日：2020-05-22
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： DONAHUE, Jeffrey , SIMONYAN, Karen
IPC分类号： G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a generator neural network and an encoder neural network. The generator neural network generates, based on a set of latent values, data items which are samples of a distribution. The encoder neural network generates a set of latent values for a respective data item. The training method comprises jointly training the generator neural network, the encoder neural network and a discriminator neural network configured to distinguish between samples generated by the generator network and samples of the distribution which are not generated by the generator network. The discriminator neural network is configured to distinguish by processing, by the discriminator neural network, an input pair comprising a sample part and a latent part. The training is based upon a loss function comprising a joint discriminator loss term based upon the sample and latent parts of the input pair processed by the discriminator neural network and at least one single discriminator loss term based upon only one of the sample or latent parts of the input pair.

3. 发明申请

WO2020234449A1 GENERATIVE ADVERSARIAL NETWORKS WITH TEMPORAL AND SPATIAL DISCRIMINATORS FOR EFFICIENT VIDEO GENERATION 审中-公开
公开(公告)号：WO2020234449A1
公开(公告)日：2020-11-26
申请号：PCT/EP2020/064270
申请日：2020-05-22
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： CLARK, Aidan , DONAHUE, Jeffrey , SIMONYAN, Karen
IPC分类号： G06N3/04 , G06N3/08
摘要： The present disclosure proposes the use of a dual discriminator network that comprises a temporal discriminator network for discriminating based on temporal features of a series of images and a spatial discriminator network for discriminating based on spatial features of individual images. The training methods described herein provide improvements in computational efficiency. This is achieved by applying the spatial discriminator network to a set of one or more images that have reduced temporal resolution and applying the temporal discriminator network to a set of images that have reduced spatial resolution. This allows each of the discriminator networks to be applied more efficiently in order to produce a discriminator score for use in training the generator, whilst maintaining accuracy of the discriminator network. In addition, this allows a generator network to be trained to more accurately generate sequences of images, through the use of the improved discriminator.

4. 发明申请

WO2018211145A1 GENERATING OUTPUT EXAMPLES USING BIT BLOCKS 审中-公开
公开(公告)号：WO2018211145A1
公开(公告)日：2018-11-22
申请号：PCT/EP2018/063305
申请日：2018-05-22
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , ELSEN, Erich Konrad
IPC分类号： G06N3/04 , G06N3/08
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. One of the methods includes receiving a request to generate an output example of a particular type, accessing dependency data, and generating the output example by, at each of a plurality of generation time steps: identifying one or more current blocks for the generation time step, wherein each current block is a block for which the values of the bits in all of the other blocks identified in the dependency for the block have already been generated; and generating the values of the bits in the current blocks for the generation time step conditioned on, for each current block, the already generated values of the bits in the other blocks identified in the dependency for the current block.

5. 发明申请

WO2020058177A1 MACHINE LEARNING FOR DETERMINING PROTEIN STRUCTURES 审中-公开
公开(公告)号：WO2020058177A1
公开(公告)日：2020-03-26
申请号：PCT/EP2019/074676
申请日：2019-09-16
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： SENIOR, Andrew W. , KIRKPATRICK, James , SIFRE, Laurent , EVANS, Richard Andrew , PENEDONES, Hugo , QIN, Chongli , SUN, Ruoxi , SIMONYAN, Karen , JUMPER, John
IPC分类号： G16B15/20 , G16B40/20 , G06N3/00 , G16H50/20
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises, at each of one or more iterations: determining an alternative predicted structure of a given protein defined by alternative values of structure parameters; processing, using a geometry neural network, a network input comprising: (i) a representation of a sequence of amino acid residues in the given protein, and (ii) the alternative values of the structure parameters, to generate an output characterizing an alternative geometry score that is an estimate of a similarity measure between the alternative predicted structure and the actual structure of the given protein.

6. 发明申请

WO2019155054A1 GENERATING OUTPUT EXAMPLES USING RECURRENT NEURAL NETWORKS CONDITIONED ON BIT VALUES 审中-公开
公开(公告)号：WO2019155054A1
公开(公告)日：2019-08-15
申请号：PCT/EP2019/053300
申请日：2019-02-11
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , ELSEN, Erich Konrad
IPC分类号： G06N3/04
CPC分类号： G06N3/0445
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output examples using neural networks. One of the methods includes, at each generation time step, processing a first recurrent input comprising an N-bit output value at the preceding generation time step in the sequence using a recurrent neural network and in accordance with a hidden state to generate a first score distribution; selecting, using the first score distribution, values for the first half of the N bits; processing a second recurrent input comprising (i) the N-bit output value at the preceding generation time step and (ii) the values for the first half of the N bits using the recurrent neural network and in accordance with the same hidden state to generate a second score distribution; and selecting, using the second score distribution, values for the second half of the N bits of the output value.

7. 发明申请

WO2018048934A1 GENERATING AUDIO USING NEURAL NETWORKS 审中-公开
标题翻译：用神经网络产生音频
公开(公告)号：WO2018048934A1
公开(公告)日：2018-03-15
申请号：PCT/US2017/050320
申请日：2017-09-06
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： VAN DEN OORD, Aaron Gerard Antonius , DIELEMAN, Sander Etienne Lea , KALCHBRENNER, Nal Emmerich , SIMONYAN, Karen , VINYALS, Oriol
IPC分类号： G06N3/04
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence of audio data that comprises a respective audio sample at each of a plurality of time steps. One of the methods includes, for each of the time steps: providing a current sequence of audio data as input to a convolutional subnetwork, wherein the current sequence comprises the respective audio sample at each time step that precedes the time step in the output sequence, and wherein the convolutional subnetwork is configured to process the current sequence of audio data to generate an alternative representation for the time step; and providing the alternative representation for the time step as input to an output layer, wherein the output layer is configured to: process the alternative representation to generate an output that defines a score distribution over a plurality of possible audio samples for the time step.
摘要翻译：包括在计算机存储介质上编码的计算机程序的方法，系统和装置，用于生成音频数据的输出序列，该音频数据的输出序列在多个时间步骤中的每个时间步骤包括相应的音频样本。对于每个时间步骤，这些方法之一包括：提供音频数据的当前序列作为卷积子网络的输入，其中当前序列包括在输出序列中的时间步长之前的每个时间步骤处的相应音频样本，且其中所述卷积子网络经配置以处理所述当前音频数据序列以产生所述时间步骤的替代表示; 以及将所述时间步长的所述替代表示作为输入提供给输出层，其中所述输出层被配置为：处理所述替代表示以产生定义所述时间步骤的多个可能音频样本上的得分分布的输出。 / p>

8. 发明申请

WO2022171635A1 SEQUENCE-TO SEQUENCE NEURAL NETWORK SYSTEMS USING LOOK AHEAD TREE SEARCH 审中-公开
公开(公告)号：WO2022171635A1
公开(公告)日：2022-08-18
申请号：PCT/EP2022/053035
申请日：2022-02-08
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： LEBLOND, Rémi Bertrand Francis , ALAYRAC, Jean-Baptiste , SIFRE, Laurent , PÎSLAR, Miruna , LESPIAU, Jean-Baptiste , ANTONOGLOU, Ioannis , SIMONYAN, Karen , SILVER, David , VINYALS, Oriol
IPC分类号： G06N3/08 , G06N5/00 , G06N3/04
摘要： A computer-implemented method for generating an output token sequence from an input token sequence. The method combines a look ahead tree search, such as a Monte Carlo tree search, with a sequence-to-sequence neural network system. The sequence-to-sequence neural network system has a policy output defining a next token probability distribution, and may include a value neural network providing a value output to evaluate a sequence. An initial partial output sequence is extended using the look ahead tree search guided by the policy output and, in implementations, the value output, of the sequence-to-sequence neural network system until a complete output sequence is obtained.

9. 发明申请

WO2021156511A1 RECURRENT UNIT FOR GENERATING OR PROCESSING A SEQUENCE OF IMAGES 审中-公开
公开(公告)号：WO2021156511A1
公开(公告)日：2021-08-12
申请号：PCT/EP2021/052980
申请日：2021-02-08
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： LUC, Pauline , CLARK, Aidan , DIELEMAN, Sander Etienne Lea , SIMONYAN, Karen
IPC分类号： G06N3/04 , G06N3/08 , G06T11/00 , G06T3/40 , G06T7/10
摘要： A recurrent unit is proposed which, at each of a series of time steps receives a corresponding input vector and generates an output at the time step having at least one component for each of a two-dimensional array of pixels. The recurrent unit is configured, at each of the series of time steps except the first, to receive the output of the recurrent unit at the preceding time step, and to apply to the output of the recurrent unit at the preceding time step at least one convolution which depends on the input vector at the time step. The convolution further depends upon the output of the recurrent unit at the preceding time step. This convolution generates a warped dataset which has at least one component for each pixel of the array. The output of the recurrent unit at each time step is based on the warped dataset and the input vector.

10. 发明申请

WO2020058176A1 MACHINE LEARNING FOR DETERMINING PROTEIN STRUCTURES 审中-公开
公开(公告)号：WO2020058176A1
公开(公告)日：2020-03-26
申请号：PCT/EP2019/074674
申请日：2019-09-16
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： SENIOR, Andrew W. , KIRKPATRICK, James , SIFRE, Laurent , EVANS, Richard Andrew , PENEDONES, Hugo , QIN, Chongli , SUN, Ruoxi , SIMONYAN, Karen , JUMPER, John
IPC分类号： G16B15/20 , G16B40/20 , G06N3/00 , G16H50/20
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing protein structure prediction. In one aspect, a method comprises generating a distance map for a given protein, wherein the given protein is defined by a sequence of amino acid residues arranged in a structure, wherein the distance map characterizes estimated distances between the amino acid residues in the structure, comprising: generating a plurality of distance map crops, wherein each distance map crop characterizes estimated distances between (i) amino acid residues in each of one or more respective first positions in the sequence and (ii) amino acid residues in each of one or more respective second positions in the sequence in the structure of the protein, wherein the first positions are a proper subset of the sequence; and generating the distance map for the given protein using the plurality of distance map crops.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式