公开(公告)号：US20200005147A1

公开(公告)日：2020-01-02

申请号：US16565245

申请日：2019-09-09

Applicant: DeepMind Technologies Limited

Inventor： Edward Thomas Grefenstette ,  Karl Moritz Hermann ,  Mustafa Suleyman ,  Philip Blunsom

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

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.

公开(公告)号：US20190139270A1

公开(公告)日：2019-05-09

申请号：US16236045

申请日：2018-12-28

Applicant: DeepMind Technologies Limited

Inventor： Jeffrey De Fauw ,  Joseph R. Ledsam ,  Bernardino Romera-Paredes ,  Stanislav Nikolov ,  Nenad Tomasev ,  Samuel Blackwell ,  Harry Askham ,  Xavier Glorot ,  Balaji Lakshminarayanan ,  Trevor Back ,  Mustafa Suleyman ,  Pearse A. Keane ,  Olaf Ronneberger ,  Julien Robert Michel Cornebise

IPC: G06T11/00 ,  G06T7/00 ,  G06K9/62

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a final classification output for an image of eye tissue. The image is provided as input to each of one or more segmentation neural networks to obtain one or more segmentation maps of the eye tissue in the image. A respective classification input is generated from each of the segmentation maps. For each of the segmentation maps, the classification input for the segmentation map is provided as input to each of one or more classification neural networks to obtain, for each segmentation map, a respective classification output from each classification neural network. A final classification output for the image is generated from the respective classification outputs for each of the segmentation maps.

公开(公告)号：US08644607B1

公开(公告)日：2014-02-04

申请号：US13801027

申请日：2013-03-13

Applicant: DeepMind Technologies Limited

Inventor： Benjamin Kenneth Coppin ,  Mustafa Suleyman ,  Arun Nair

IPC: G06K9/00

CPC classification number: G06F17/30262 ,  G06K9/00 ,  G06K9/46 ,  G06K2009/4666

Abstract: A method is described for processing an image to generate a signature which is characteristic of a pattern within the image. The method includes: receiving an image; overlaying a window at multiple locations on the image to define a plurality of sub-images within the image, with each sub-image each having a plurality of pixels having a luminance level; determining a luminance value for each sub-image where the luminance value is derived from the luminance levels of the plurality of pixels; and combining the luminance values for each of the sub-images to form the signature. The combining is such that the signature is independent of the location of each sub-image. A method of creating a database of images using the method of generating signatures is also described.

Abstract translation: 描述了一种用于处理图像以生成图像中的图案的特征的签名的方法。 该方法包括：接收图像; 在图像上的多个位置处叠加窗口以在图像内定义多个子图像，每个子图像各自具有具有亮度级别的多个像素; 确定从多个像素的亮度级导出亮度值的每个子图像的亮度值; 以及组合每个子图像的亮度值以形成签名。 组合使得签名独立于每个子图像的位置。 还描述了使用生成签名的方法来创建图像数据库的方法。