DeepMind Technologies Limited patent applications on September 26th, 2024
Patent Applications by DeepMind Technologies Limited on September 26th, 2024
DeepMind Technologies Limited: 5 patent applications
DeepMind Technologies Limited has applied for patents in the areas of G06N3/08 (3), G06N3/044 (2), G06F40/30 (1), G06F17/16 (1), G06N3/048 (1) G06F40/30 (1), G06N3/044 (1), G06N3/092 (1), G06N7/01 (1), G16B15/20 (1)
With keywords such as: network, input, attention, neural, observation, current, protein, computer, configured, and layer in patent application abstracts.
Patent Applications by DeepMind Technologies Limited
Inventor(s): Karl Moritz Hermann of Berlin (DE) for deepmind technologies limited, Philip Blunsom of Oxford (GB) for deepmind technologies limited, Felix George Hill of London (GB) for deepmind technologies limited
IPC Code(s): G06F40/30, G06F17/16, G06N3/08
CPC Code(s): G06F40/30
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. in one aspect, a system includes a language encoder model that is configured to receive a text string in a particular natural language, and process the text string to generate a text embedding of the text string. the system includes an observation encoder neural network that is configured to receive an observation characterizing a state of the environment, and process the observation to generate an observation embedding of the observation. the system includes a subsystem that is configured to obtain a current text embedding of a current text string and a current observation embedding of a current observation. the subsystem is configured to select an action to be performed by the agent in response to the current observation.
20240320469. GATED ATTENTION NEURAL NETWORKS_simplified_abstract_(deepmind technologies limited)
Inventor(s): Emilio Parisotto of London (GB) for deepmind technologies limited, Hasuk Song of London (GB) for deepmind technologies limited, Jack William Rae of London (GB) for deepmind technologies limited, Siddhant Madhu Jayakumar of London (GB) for deepmind technologies limited, Maxwell Elliot Jaderberg of London (GB) for deepmind technologies limited, Razvan Pascanu of Letchworth Garden City (GB) for deepmind technologies limited, Caglar Gulcehre of Lausanne (CH) for deepmind technologies limited
IPC Code(s): G06N3/044, G06N3/048, G06N3/08
CPC Code(s): G06N3/044
Abstract: a system including an attention neural network that is configured to receive an input sequence and to process the input sequence to generate an output is described. the attention neural network includes: an attention block configured to receive a query input, a key input, and a value input that are derived from an attention block input. the attention block includes an attention neural network layer configured to: receive an attention layer input derived from the query input, the key input, and the value input, and apply an attention mechanism to the query input, the key input, and the value input to generate an attention layer output for the attention neural network layer; and a gating neural network layer configured to apply a gating mechanism to the attention block input and the attention layer output of the attention neural network layer to generate a gated attention output.
Inventor(s): Anirudh Goyal of London (GB) for deepmind technologies limited, Andrea Banino of London (GB) for deepmind technologies limited, Abram Luke Friesen of London (GB) for deepmind technologies limited, Theophane Guillaume Weber of London (GB) for deepmind technologies limited, Adrià Puigdomènech Badia of London (GB) for deepmind technologies limited, Nan Ke of London (GB) for deepmind technologies limited, Simon Osindero of London (GB) for deepmind technologies limited, Timothy Paul Lillicrap of London (GB) for deepmind technologies limited, Charles Blundell of London (GB) for deepmind technologies limited
IPC Code(s): G06N3/092, G06N3/044, G06N3/0455, G06N3/084
CPC Code(s): G06N3/092
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling a reinforcement learning agent in an environment to perform a task using a retrieval-augmented action selection process. one of the methods includes receiving a current observation characterizing a current state of the environment; processing an encoder network input comprising the current observation to determine a policy neural network hidden state that corresponds to the current observation; maintaining a plurality of trajectories generated as a result of the reinforcement learning agent interacting with the environment; selecting one or more trajectories from the plurality of trajectories; updating the policy neural network hidden state using update data determined from the one or more selected trajectories; and processing the updated hidden state using a policy neural network to generate a policy output that specifies an action to be performed by the agent in response to the current observation.
Inventor(s): Sumanth Dathathri of London (GB) for deepmind technologies limited, Abigail Elizabeth See of London (GB) for deepmind technologies limited, Borja De Balle Pigem of London (GB) for deepmind technologies limited, Sumedh Kedar Ghaisas of London (GB) for deepmind technologies limited, Pushmeet Kohli of London (GB) for deepmind technologies limited, Po-Sen Huang of London (GB) for deepmind technologies limited, Johannes Maximilian Welbl of London (GB) for deepmind technologies limited
IPC Code(s): G06N7/01
CPC Code(s): G06N7/01
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for watermarking a digital object generated by a machine learning model. the digital object is defined by a sequence of tokens. the watermarking involves modifying a probability distribution of the tokens by applying a succession of watermarking stages.
Inventor(s): Richard Andrew Evans of London (GB) for deepmind technologies limited, Michael James O'Neill of London (GB) for deepmind technologies limited, Alexander Pritzel of London (GB) for deepmind technologies limited, Natasha Olegovna Antropova of London (GB) for deepmind technologies limited, Timothy Frederick Goldie Green of London (GB) for deepmind technologies limited, John Jumper of London (GB) for deepmind technologies limited
IPC Code(s): G16B15/20, G06N3/08, G16B15/30, G16B40/20
CPC Code(s): G16B15/20
Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting a structure of a protein that comprises a plurality of amino acid chains using a protein structure prediction neural network, where each chain comprises a respective sequence of amino acids. in one aspect, a method comprises: receiving a network input for the protein structure prediction neural network, wherein the network input characterizes the protein; processing the network input characterizing the protein using the protein structure prediction neural network to generate a network output that characterizes a predicted structure of the protein; and determining the predicted structure of the protein based on the network output.
DeepMind Technologies Limited patent applications on September 26th, 2024
