专利检索 ap:("DeepMind Technologies Limited") AND inv:"BOTVINICK, Matthew" 第 1 页

1.

发明公开
GENERATING SEQUENCES OF DATA ELEMENTS USING CROSS-ATTENTION OPERATIONS 审中-公开

公开(公告)号：EP4453791A1

公开(公告)日：2024-10-30

申请号：EP23702436.9

申请日：2023-01-27

申请人： DeepMind Technologies Limited

发明人： HAWTHORNE, Curtis Glenn-Macway , JAEGLE, Andrew Coulter , CANGEA, Catalina-Codruta , BORGEAUD DIT AVOCAT, Sebastian , NASH, Charlie Thomas Curtis , MALINOWSKI, Mateusz , DIELEMAN, Sander Etienne Lea , VINYALS, Oriol , BOTVINICK, Matthew , SIMON, Ian Stuart , SHEAHAN, Hannah Rachel , ZEGHIDOUR, Neil , ALAYRAC, Jean-Baptiste , CARREIRA, Joao , ENGEL, Jesse

IPC分类号： G06N3/045 , G06N3/09 , G06N3/084

2.

发明公开
LEARNING VISUAL CONCEPTS USING NEURAL NETWORKS 审中-公开

公开(公告)号：EP3602402A1

公开(公告)日：2020-02-05

申请号：EP18740193.0

申请日：2018-07-11

申请人： Deepmind Technologies Limited

发明人： LERCHNER, Alexander , HIGGINS, Irina , SONNERAT, Nicolas , PAL, Arka Tilak , HASSABIS, Demis , MATTHEY-DE-L`ENDROIT, Loic , BURGESS, Christopher Paul , BOTVINICK, Matthew

IPC分类号： G06K9/62

3.

发明公开
UNSUPERVISED LEARNING OF OBJECT REPRESENTATIONS FROM VIDEO SEQUENCES USING ATTENTION OVER SPACE AND TIME 审中-公开

公开(公告)号：EP4315171A1

公开(公告)日：2024-02-07

申请号：EP22734118.7

申请日：2022-05-27

申请人： DeepMind Technologies Limited

发明人： KABRA, Rishabh , ZORAN, Daniel , ERDOGAN, Goker , CRESWELL, Antonia Phoebe Nina , MATTHEY-DE-L'ENDROIT, Loic , BOTVINICK, Matthew , LERCHNER, Alexander , BURGESS, Christopher Paul

IPC分类号： G06N3/04 , G06N3/08

4.

发明公开
NEURAL NETWORKS IMPLEMENTING ATTENTION OVER OBJECT EMBEDDINGS FOR OBJECT-CENTRIC VISUAL REASONING 审中-公开

公开(公告)号：EP4200746A1

公开(公告)日：2023-06-28

申请号：EP21786471.9

申请日：2021-10-01

申请人： DeepMind Technologies Limited

发明人： DING, Fengning , SANTORO, Adam Anthony , HILL, Felix George , BOTVINICK, Matthew , PILOTO, Luis

IPC分类号： G06K9/00

5.

发明公开
LEARNING VISUAL CONCEPTS USING NEURAL NETWORKS 审中-公开

公开(公告)号：EP4053740A1

公开(公告)日：2022-09-07

申请号：EP22169342.7

申请日：2018-07-11

申请人： DeepMind Technologies Limited

发明人： LERCHNER, Alexander , HIGGINS, Irina , SONNERAT, Nicolas , PAL, Arka Tilak , HASSABIS, Demis , MATTHEY-DE-L`ENDROIT, Loic , BURGESS, Christopher Paul , BOTVINICK, Matthew

IPC分类号： G06K9/62 , G06V20/70

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.