DeepMind Technologies Limited patent applications on February 13th, 2025

From WikiPatents
Jump to navigation Jump to search

Patent Applications by DeepMind Technologies Limited on February 13th, 2025

DeepMind Technologies Limited: 2 patent applications

DeepMind Technologies Limited has applied for patents in the areas of C07D239/47 (1), A61P35/00 (1), C07C275/36 (1), G06N3/045 (1), G06F16/22 (1) C07D239/47 (1), G06N3/045 (1)

With keywords such as: memory, data, locations, configured, generate, time, observation, environment, read, and representation in patent application abstracts.



Patent Applications by DeepMind Technologies Limited

20250051289. TRAINING AN UNSUPERVISED MEMORY-BASED PREDICTION SYSTEM TO LEARN COMPRESSED REPRESENTATIONS OF AN ENVIRONMENT_simplified_abstract_(deepmind technologies limited)

Inventor(s): Gregory Duncan Wayne of London (GB) for deepmind technologies limited, Chia-Chun Hung of London (GB) for deepmind technologies limited, David Antony Amos of Hassocks West Sussex (GB) for deepmind technologies limited, Mehdi Mirza Mohammadi of London (GB) for deepmind technologies limited, Arun Ahuja of London (GB) for deepmind technologies limited, Timothy Paul Lillicrap of London (GB) for deepmind technologies limited

IPC Code(s): C07D239/47, A61P35/00, C07C275/36

CPC Code(s): C07D239/47



Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a memory-based prediction system configured to receive an input observation characterizing a state of an environment interacted with by an agent and to process the input observation and data read from a memory to update data stored in the memory and to generate a latent representation of the state of the environment. the method comprises: for each of a plurality of time steps: processing an observation for the time step and data read from the memory to: (i) update the data stored in the memory, and (ii) generate a latent representation of the current state of the environment as of the time step; and generating a predicted return that will be received by the agent as a result of interactions with the environment after the observation for the time step is received.


20250053780. SCALABLE AND COMPRESSIVE NEURAL NETWORK DATA STORAGE SYSTEM_simplified_abstract_(deepmind technologies limited)

Inventor(s): Jack William Rae of London (GB) for deepmind technologies limited, Timothy Paul Lillicrap of London (GB) for deepmind technologies limited, Sergey Bartunov of London (GB) for deepmind technologies limited

IPC Code(s): G06N3/045, G06F16/22, G06N3/08

CPC Code(s): G06N3/045



Abstract: a system for compressed data storage using a neural network. the system comprises a memory comprising a plurality of memory locations configured to store data; a query neural network configured to process a representation of an input data item to generate a query; an immutable key data store comprising key data for indexing the plurality of memory locations; an addressing system configured to process the key data and the query to generate a weighting associated with the plurality of memory locations; a memory read system configured to generate output memory data from the memory based upon the generated weighting associated with the plurality of memory locations and the data stored at the plurality of memory locations; and a memory write system configured to write received write data to the memory based upon the generated weighting associated with the plurality of memory locations.


DeepMind Technologies Limited patent applications on February 13th, 2025