DeepMind Technologies Limited patent applications on July 4th, 2024
Patent Applications by DeepMind Technologies Limited on July 4th, 2024
DeepMind Technologies Limited: 4 patent applications
DeepMind Technologies Limited has applied for patents in the areas of G06N3/08 (2), G06F16/2457 (1), G06F40/284 (1), G06N3/045 (1), G06F17/18 (1) G06F16/24573 (1), G06N3/045 (1), G06N3/08 (1), G06V10/771 (1)
With keywords such as: respective, score, expanded, pixel, object, latent, neural, updating, network, and sequence in patent application abstracts.
Patent Applications by DeepMind Technologies Limited
Inventor(s): Domenic Joseph Donato of Oviedo FL (US) for deepmind technologies limited, Christopher James Dyer of London (GB) for deepmind technologies limited, Rémi Leblond of Cachan (FR) for deepmind technologies limited
IPC Code(s): G06F16/2457, G06F40/284
CPC Code(s): G06F16/24573
Abstract: methods and systems for beam search decoding. one of the methods includes initializing beam data specifying a set of k candidate output sequences and a respective total score for each of the candidate output sequences; updating the beam data at each of a plurality of decoding steps, comprising, at each decoding step: generating a score distribution that comprises a respective score for each token in the vocabulary; identifying a plurality of expanded sequences; generating, for each expanded sequence, a respective backwards-looking score; generating, for each expanded sequence, a respective forward-looking score; computing, for each expanded sequence, a respective total score from the respective forward-looking score for the expanded sequence and the respective backwards-looking score for the expanded sequence; and updating the set of k candidate output sequences using the respective total scores for the expanded sequences.
Inventor(s): Iain Robert Dunning of New York NY (US) for deepmind technologies limited, Wojciech Czarnecki of London (GB) for deepmind technologies limited, Maxwell Elliot Jaderberg of London (GB) for deepmind technologies limited
IPC Code(s): G06N3/045, G06F17/18, G06N3/047, G06N3/08
CPC Code(s): G06N3/045
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for reinforcement learning. one of the methods includes selecting an action to be performed by the agent using both a slow updating recurrent neural network and a fast updating recurrent neural network that receives a fast updating input that includes the hidden state of the slow updating recurrent neural network.
Inventor(s): Jingwei Zhang of London (GB) for deepmind technologies limited, Arunkumar Byravan of London (GB) for deepmind technologies limited, Jost Tobias Springenberg of London (GB) for deepmind technologies limited, Martin Riedmiller of Balgheim (DE) for deepmind technologies limited, Nicolas Manfred Otto Heess of London (GB) for deepmind technologies limited, Leonard Hasenclever of London (GB) for deepmind technologies limited, Abbas Abdolmaleki of London (GB) for deepmind technologies limited, Dushyant Rao of London (GB) for deepmind technologies limited
IPC Code(s): G06N3/08
CPC Code(s): G06N3/08
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using jumpy trajectory decoder neural networks.
Inventor(s): Rishabh Kabra of London (GB) for deepmind technologies limited, Daniel Zoran of London (GB) for deepmind technologies limited, Goker Erdogan of London (GB) for deepmind technologies limited, Antonia Phoebe Nina Creswell of London (GB) for deepmind technologies limited, Loic Matthey-de-l'Endroit of London (GB) for deepmind technologies limited, Matthew Botvinick of Philadelphia PA (US) for deepmind technologies limited, Alexander Lerchner of London (GB) for deepmind technologies limited, Christopher Paul Burgess of Purley (GB) for deepmind technologies limited
IPC Code(s): G06V10/771, G06T9/00, G06V10/44, G06V10/82
CPC Code(s): G06V10/771
Abstract: a computer-implemented video generation neural network system, configured to determine a value for each of a set of object latent variables by sampling from a respective prior object latent distribution for the object latent variable. the system comprises a trained image frame decoder neural network configured to, for each pixel of each generated image frame and for each generated image frame time step process determined values of the object latent variables to determine parameters of a pixel distribution for each of the object latent variables, combine the pixel distributions for each of the object latent variables to determine a combined pixel distribution, and sample from the combined pixel distribution to determine a value for the pixel and for the time step.
DeepMind Technologies Limited patent applications on July 4th, 2024
