DeepMind Technologies Limited patent applications on December 12th, 2024
Patent Applications by DeepMind Technologies Limited on December 12th, 2024
DeepMind Technologies Limited: 4 patent applications
DeepMind Technologies Limited has applied for patents in the areas of G06N3/08 (2), G06N3/0455 (1), G06N3/092 (1), G16B15/00 (1), G06N3/02 (1) G06N3/0455 (1), G06N3/08 (1), G06N3/092 (1), G16B15/00 (1)
With keywords such as: action, selection, computer, sequence, amino, training, network, neural, embedding, and pair in patent application abstracts.
Patent Applications by DeepMind Technologies Limited
Inventor(s): Nikolay Savinov of London (GB) for deepmind technologies limited, Junyoung Chung of London (GB) for deepmind technologies limited, Mikolaj Binkowski of London (GB) for deepmind technologies limited, Aaron Gerard Antonius van den Oord of London (GB) for deepmind technologies limited, Erich Konrad Elsen of Naperville IL (US) for deepmind technologies limited
IPC Code(s): G06N3/0455, G06N3/08
CPC Code(s): G06N3/0455
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using a non-auto-regressive neural network.
Inventor(s): Oleg O. Sushkov of London (GB) for deepmind technologies limited, Todor Bozhinov Davchev of Edinburgh (GB) for deepmind technologies limited, Jonathan Karl Scholz 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 computer storage media, for training a reinforcement learning system to select actions to be performed by an agent interacting with an environment to perform a particular task. in one aspect, one of the methods includes obtaining a training sequence comprising a respective training observations at each of a plurality of time steps; obtaining demonstration data comprising one or more demonstration sequences; generating a new training sequence from the training sequence and the demonstration data; and training the goal-conditioned policy neural network on the new training sequence through reinforcement learning.
20240412072. NEURAL POPULATION LEARNING_simplified_abstract_(deepmind technologies limited)
Inventor(s): Siqi Liu of London (GB) for deepmind technologies limited, Luke Christopher Marris of London (GB) for deepmind technologies limited, Nicolas Manfred Otto Heess of London (GB) for deepmind technologies limited, Marc Lanctot of London (GB) for deepmind technologies limited
IPC Code(s): G06N3/092
CPC Code(s): G06N3/092
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment using a population of action selection policies that are jointly represented by a population action selection neural network. in one aspect, a method comprises, at each of a plurality of time steps: obtaining an observation characterizing a current state of the environment at the time step; selecting a target action selection policy from the population of action selection policies; processing a network input comprising: (i) the observation, and (ii) a strategy embedding representing the target action selection policy, using the population action selection neural network to generate an action selection output; and selecting an action to be performed by the agent at the time step using the action selection output.
Inventor(s): John Jumper of London (GB) for deepmind technologies limited, Andrew W. Senior of London (GB) for deepmind technologies limited, Richard Andrew Evans of London (GB) for deepmind technologies limited, Russell James Bates of London (GB) for deepmind technologies limited, Mikhail Figurnov of London (GB) for deepmind technologies limited, Alexander Pritzel of London (GB) for deepmind technologies limited, Timothy Frederick Goldie Green of London (GB) for deepmind technologies limited
IPC Code(s): G16B15/00, G06N3/02
CPC Code(s): G16B15/00
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a predicted structure of a protein that is specified by an amino acid sequence. in one aspect, a method comprises: obtaining a multiple sequence alignment for the protein; determining, from the multiple sequence alignment and for each pair of amino acids in the amino acid sequence of the protein, a respective initial embedding of the pair of amino acids; processing the initial embeddings of the pairs of amino acids using a pair embedding neural network comprising a plurality of self-attention neural network layers to generate a final embedding of each pair of amino acids; and determining the predicted structure of the protein based on the final embedding of each pair of amino acids.
DeepMind Technologies Limited patent applications on December 12th, 2024
