View source for DeepMind Technologies Limited patent applications on 2025-05-22

=Patent Applications by DeepMind Technologies Limited on May 22nd, 2025=

[[:Category:DeepMind Technologies Limited|DeepMind Technologies Limited]]: 2 patent applications[[Category:DeepMind Technologies Limited]]

DeepMind Technologies Limited has applied for patents in the areas of [[:Category:CPC_G06F16/9024|G06F16/9024]] ({Graphs; Linked lists  ( takes precedence)}, 1), [[:Category:CPC_H04N19/189|H04N19/189]] (characterised by the adaptation method, adaptation tool or adaptation type used for the adaptive coding, 1)

With keywords such as: computer, methods, systems, apparatus, including, programs, encoded, storage, media, generating in patent application abstracts.

Top Inventors:
* [[:Category:Sivaramakrishnan Swaminathan of Mountain View CA US|Sivaramakrishnan Swaminathan of Mountain View CA US]] (1 patents)
* [[:Category:Meet Kirankumar Dave of Santa Clara CA US|Meet Kirankumar Dave of Santa Clara CA US]] (1 patents)
* [[:Category:Miguel Lazaro-Gredilla of Union City CA US|Miguel Lazaro-Gredilla of Union City CA US]] (1 patents)
* [[:Category:Dileep George of Sunnyvale CA US|Dileep George of Sunnyvale CA US]] (1 patents)
* [[:Category:Emilien Dupont of London  GB|Emilien Dupont of London  GB]] (1 patents)

====Patent Applications by DeepMind Technologies Limited====

[[20250165532. FAST EXPLORATION LEARNING LATENT GRAPH MODELS (DeepMind Technologies Limited)]]

Abstract: methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a graph model representing an environment being interacted with by an agent. in one aspect, one of the methods include: obtaining experience data; using the experience data to update a visitation count for each of one or more state-action pairs represented by the graph model; and at each of multiple environment exploration steps: computing a utility measure for each of the one or more state-action pairs represented by the graph model; determining, based on the utility measures, a sequence of one or more planned actions that have an information gain that satisfies a threshold; and controlling the agent to perform the sequence of one or more planned actions to cause the environment to transition from a state characterized by a last observation received after a last action in the experience data into a different state.
[[Category:deepmind technologies limited]]

[[20250168368. HIGH-PERFORMANCE LOW-COMPLEXITY NEURAL COMPRESSION SINGLE IMAGE, VIDEO OR AUDIO DATA (DeepMind Technologies Limited)]]

Abstract: methods, systems, and apparatus, including computer programs encoded on a computer storage medium for encoding input data comprising input data values corresponding to respective input data grid points of an input data grid, such as image, video or audio data.
[[Category:deepmind technologies limited]]