DeepMind Technologies Limited patent applications on August 8th, 2024
Patent Applications by DeepMind Technologies Limited on August 8th, 2024
DeepMind Technologies Limited: 4 patent applications
DeepMind Technologies Limited has applied for patents in the areas of G06N3/091 (1), G06N3/092 (1), G06N3/045 (1), G10L15/06 (1), G10L25/30 (1) G06N3/091 (1), G06N3/092 (1), G10L15/063 (1), H04N19/149 (1)
With keywords such as: neural, video, network, training, agent, methods, speech, task, computer, and constraint in patent application abstracts.
Patent Applications by DeepMind Technologies Limited
Inventor(s): Theodore Harris Moskovitz of London (GB) for deepmind technologies limited, Brendan Timothy O'Donoghue of London (GB) for deepmind technologies limited, Tom Ben Zion Zahavy of London (GB) for deepmind technologies limited, Johan Sebastian Flennerhag of London (GB) for deepmind technologies limited, Vivek Veeriah Jeya Veeraiah of London (GB) for deepmind technologies limited, Satinder Singh Baveja of Ann Arbor MI (US) for deepmind technologies limited
IPC Code(s): G06N3/091
CPC Code(s): G06N3/091
Abstract: a method is described for iteratively training a policy model, such as a neural network, of a computer-implemented action selection system to control an agent interacting with an environment to perform a task subject to one or more constraints. the task has a reward associated with performance of the task. each constraint limits to a corresponding threshold the expected value of the total of a corresponding constraint function which if the future actions of the agent are chosen according to the policy model, and each constraint is associated with a corresponding multiplier variable. in each iteration, a mixed reward function is generated based on values for the multiplier variables generated in the preceding iteration, and estimates of the rewards and the values of constraint reward functions if the actions are chosen based on the policy model generated in the preceding iteration.
Inventor(s): Gheorghe Tiberi Comanici of Montreal (CA) for deepmind technologies limited, Amelia Marita Claudia Glaese of Montreal (CA) for deepmind technologies limited, Anita Gergely of Montreal (CA) for deepmind technologies limited, Zafarali Ahmed of Montreal (CA) for deepmind technologies limited, Tyler Jackson of Montreal (CA) for deepmind technologies limited, Doina Precup of Côte Saint-Luc (CA) for deepmind technologies limited
IPC Code(s): G06N3/092, G06N3/045
CPC Code(s): G06N3/092
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling one or more computing devices to perform a task using a hierarchical agent. one of the methods includes receiving an observation characterizing a state of the one or more computing devices at the time step; selecting a gesture class for the time step using a high-level agent; processing a mid-level input using a mid-level agent neural network conditioned on the selected gesture class to generate a mid-level output that comprises parameters that define a gesture from the selected gesture class; processing a low-level input using a low-level agent neural network to generate a policy output that defines a sequence of one or more actions for interacting with the one or more computing devices; and performing the sequence of one or more actions to interact with the one or more computing devices.
20240265911. ADAPTIVE VISUAL SPEECH RECOGNITION_simplified_abstract_(deepmind technologies limited)
Inventor(s): Ioannis Alexandros Assael of London (GB) for deepmind technologies limited, Brendan Shillingford of London (GB) for deepmind technologies limited, Joao Ferdinando Gomes de Freitas of London (GB) for deepmind technologies limited
IPC Code(s): G10L15/06, G10L25/30
CPC Code(s): G10L15/063
Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing video data using an adaptive visual speech recognition model. one of the methods includes receiving a video that includes a plurality of video frames that depict a first speaker: obtaining a first embedding characterizing the first speaker; and processing a first input comprising (i) the video and (ii) the first embedding using a visual speech recognition neural network having a plurality of parameters, wherein the visual speech recognition neural network is configured to process the video and the first embedding in accordance with trained values of the parameters to generate a speech recognition output that defines a sequence of one or more words being spoken by the first speaker in the video.
Inventor(s): Anton Zhernov of London (GB) for deepmind technologies limited, Chenjie Gu of Sunnyvale CA (US) for deepmind technologies limited, Daniel J. Mankowitz of St. Albans (GB) for deepmind technologies limited, Julian Schrittwieser of London (GB) for deepmind technologies limited, Amol Balkishan Mandhane of London (GB) for deepmind technologies limited, Mary Elizabeth Rauh of London (GB) for deepmind technologies limited, Miaosen Wang of Sunnyvale CA (US) for deepmind technologies limited, Thomas Keisuke Hubert of London (GB) for deepmind technologies limited
IPC Code(s): H04N19/149, H04N19/172
CPC Code(s): H04N19/149
Abstract: systems and methods for training rate control neural networks through reinforcement learning. during training, reward values for training examples are generated from the current performance of the rate control neural network in encoding the video in the training example and the historical performance of the rate control neural network in encoding the video in the training example.
DeepMind Technologies Limited patent applications on August 8th, 2024
