Patent Assignment
Reel/Frame 071498/0210
Assignment of Assignor's Interest
Recorded: 2025-06-06
Pages: 38
Assignor
DEEPMIND TECHNOLOGIES LIMITED
Executed: 2025-06-03
Assignee
GDM HOLDING LLC
1600, AMPHITHEATRE PARKWAY, MOUNTAIN VIEW, CALIFORNIA, 94043
Covered Properties
(314)
Model-Free Control for Reinforcement Learning Agents
Application:
16/303,256 →
Publication:
US US20190205757A1
Interaction Networks
Application:
16/303,623 →
Publication:
US US20200320377A1
Training Machine Learning Models on Multiple Machine Learning Tasks
Application:
16/319,040 →
Publication:
US US20190236482A1
Protein Structure Prediction Using Geometric Attention Neural Networks
Machine Learning Systems with Memory Based Parameter Adaptation for Learning Fast and Slower
Scheduling Computation Graphs Using Neural Networks with Instance-Specific Proposal Distributions
Application:
16/818,932 →
Publication:
US US20200293838A1
Selecting Action Slates Using Reinforcement Learning
Olfactory Predictions Using Neural Networks
Application:
16/942,625 →
Publication:
US US20220036172A1
Generative Neural Network Systems for Generating Instruction Sequences to Control an Agent Performing a Task
Neural Network Systems Implementing Conditional Neural Processes for Efficient Learning
Training Spectral Inference Neural Networks Using Bilevel Optimization
Antisymmetric Neural Networks
High Fidelity Speech Synthesis with Adversarial Networks
Application:
17/032,578 →
Publication:
US US20210089909A1
Reinforcement Learning Using Meta-Learned Intrinsic Rewards
Graph Neural Networks Representing Physical Systems
Graph Neural Network Systems for Behavior Prediction and Reinforcement Learning in Multiple Agent Environments
Application:
17/054,632 →
Publication:
US US20210192358A1
Domain Adaptation for Robotic Control Using Self-Supervised Learning
Augmenting Neural Networks with External Memory
Imagination-Based Agent Neural Networks
Application:
17/114,324 →
Publication:
US US20210089834A1
Training Machine Learning Models Using Task Selection Policies to Increase Learning Progress
Application:
17/159,961 →
Publication:
US US20210150355A1
Reduced Computation Real Time Recurrent Learning
Determining Protein Distance Maps by Combining Distance Maps Crops
Predicting Protein Structures Using Geometry Neural Networks That Estimate Similarity Between Predicted Protein Structures and Actual Protein Structures
Aligning Sequences by Generating Encoded Representations of Data Items
Stable and Efficient Training of Adversarial Models by an Iterated Update Operation of Second Order or Higher
Application:
17/337,376 →
Publication:
US US20210383243A1
Neural Network Optimization Using Curvature Estimates Based on Recent Gradients
Self-Supervised Representation Learning Using Bootstrapped Latent Representations
Cross-Transformer Neural Network System for Few-Shot Similarity Determination and Classification
Learning Embeddings Subject to an Invariance Constraint Between Score Distributions
Application:
17/338,938 →
Publication:
US US20210383227A1
Generating Prediction Outputs Using Dynamic Graphs
Generating Audio Data Using Unaligned Text Inputs with an Adversarial Network
Reinforcement Learning Using Target Neural Networks
Application:
17/359,427 →
Publication:
US US20210374538A1
Boolean Satisfiability Problem Solving Using Restricted Boltzmann Machines
Application:
17/390,512 →
Publication:
US US20220044097A1
Autoregressively Generating Sequences of Data Elements Defining Actions to Be Performed by an Agent
Controlling an Agent to Explore an Environment Using Observation Likelihoods
Application:
17/425,200 →
Publication:
US US20220092456A1
Identifying Neural Networks That Generate Disentangled Representations
Application:
17/425,225 →
Publication:
US US20220121934A1
Energy-Based Associative Memory Neural Networks
Training a Policy Neural Network for Controlling an Agent Using Best Response Policy Iteration
Neural Network-Based Memory System with Variable Recirculation of Queries Using Memory Content
Application:
17/613,398 →
Publication:
US US20220253698A1
Hierarchical Policies for Multitask Transfer
Application:
17/613,687 →
Publication:
US US20220237488A1
Generative Adversarial Networks with Temporal and Spatial Discriminators for Efficient Video Generation
Robust Reinforcement Learning for Continuous Control with Model Misspecification
Training a Neural Network to Control an Agent Using Task-Relevant Adversarial Imitation Learning
Application:
17/625,361 →
Publication:
US US20220261639A1
Exploration Using Hyper-Models
Application:
17/639,504 →
Publication:
US US20220326663A1
Selecting Points in Continuous Spaces Using Neural Networks
Application:
17/668,050 →
Publication:
US US20220374683A1
Training a Neural Network Using Outputs of a Corruption Neural Network
Controlling Agents Using Causally Correct Environment Models
Application:
17/763,914 →
Publication:
US US20220366246A1
Training Action Selection Neural Networks Using Q-Learning Combined with Look Ahead Search
Application:
17/763,920 →
Publication:
US US20220366247A1
Fast Sparse Neural Networks
Application:
17/763,924 →
Publication:
US US20220335272A1
Training Action Selection Neural Networks Using Hindsight Modelling
Gated Linear Contextual Bandits
Depth-Parallel Training of Neural Networks
Application:
17/777,131 →
Publication:
US US20220398437A1
Planning for Agent Control Using Learned Hidden States
Application:
17/794,797 →
Publication:
US US20230073326A1
Generating Implicit Plans for Accomplishing Goals in an Environment Using Attention Operations Over Planning Embeddings
Recurrent Unit for Generating or Processing a Sequence of Images
Training Multi-Objective Neural Network Reinforcement Learning Systems
Application:
17/797,203 →
Publication:
US US20230082326A1
Reinforcement Learning with Adaptive Return Computation Schemes
Application:
17/797,878 →
Publication:
US US20230059004A1
Learning Environment Representations for Agent Control Using Predictions of Bootstrapped Latents
Learning Machine Learning Incentives by Gradient Descent for Agent Cooperation in a Distributed Multi-Agent System
Application:
17/798,111 →
Publication:
US US20230076192A1
Persistent Message Passing for Graph Neural Networks
Determining a Distribution of Atom Coordinates of a Macromolecule from Images Using Auto-Encoders
Application:
17/849,269 →
Publication:
US US20220415453A1
Neural Networks for Selecting Actions to Be Performed by a Robotic Agent
System and Method for Training a Sparse Neural Network Whilst Maintaining Sparsity
Application:
17/914,035 →
Publication:
US US20230124177A1
Generating Spatial Embeddings by Integrating Agent Motion and Optimizing a Predictive Objective
Learning Options for Action Selection with Meta-Gradients in Multi-Task Reinforcement Learning
Application:
17/918,365 →
Publication:
US US20230144995A1
Optimizing Algorithms for Hardware Devices
Application:
17/959,210 →
Publication:
US US20240127045A1
Neural Networks with Transformed Activation Function Layers
Application:
17/959,232 →
Publication:
US US20230107247A1
Compositional Generalization for Reinforcement Learning
Application:
17/960,051 →
Publication:
US US20230107460A1
Dynamic Entity Representations for Sequence Generation
Application:
17/960,775 →
Publication:
US US20230108579A1
Distributed Top K Computation
Semi-Supervised Keypoint Based Models
Training an Action Selection System Using Relative Entropy Q-Learning
Application:
18/008,838 →
Publication:
US US20230214649A1
Aligning Entities Using Neural Networks
Training Action Selection Neural Networks Using Auxiliary Tasks of Controlling Observation Embeddings
Off-Line Learning for Robot Control Using a Reward Prediction Model
Training Video Data Generation Neural Networks Using Video Frame Embeddings
Application:
18/020,856 →
Publication:
US US20230306258A1
Controlling Agents Using Relative Variational Intrinsic Control
Application:
18/025,304 →
Publication:
US US20230325635A1
Training Protein Structure Prediction Neural Networks Using Reduced Multiple Sequence Alignments
Application:
18/025,689 →
Publication:
US US20230360734A1
Predicting Protein Structures by Sharing Information Between Multiple Sequence Alignments and Pair Embeddings
Application:
18/026,376 →
Publication:
US US20230298687A1
Simulating Physical Environments Using Graph Neural Networks
Application:
18/027,174 →
Publication:
US US20230359788A1
Predicting Symmetrical Protein Structures Using Symmetrical Expansion Transformations
Application:
18/027,571 →
Publication:
US US20240153577A1
Cross-Domain Imitation Learning Using Goal Conditioned Policies
Application:
18/028,966 →
Publication:
US US20230330846A1
Training Reinforcement Learning Agents Using Augmented Temporal Difference Learning
Neural Networks Implementing Attention Over Object Embeddings for Object-Centric Visual Reasoning
Constrained Reinforcement Learning Neural Network Systems Using Pareto Front Optimization
Application:
18/029,992 →
Publication:
US US20230368037A1
Predicting Protein Structures Using Auxiliary Folding Networks
Predicting Protein Structures Over Multiple Iterations Using Recycling
Application:
18/034,280 →
Publication:
US US20230402133A1
Predicting Protein Structures Using Protein Graphs
Application:
18/034,989 →
Publication:
US US20230410938A1
Vocabulary Selection for Text Processing Tasks Using Power Indices
Action Selection for Reinforcement Learning Using a Manager Neural Network That Generates Goal Vectors Defining Agent Objectives
Application:
18/072,175 →
Publication:
US US20230090824A1
Training Conditional Computation Neural Networks Using Reinforcement Learning
Application:
18/076,978 →
Publication:
US US20230177309A1
Large Scale Retrieval for Sequence Generation
Controlling Interactive Agents Using Multi-Modal Inputs
Generating Neural Network Outputs by Enriching Latent Embeddings Using Self-Attention and Cross-Attention Operations
Generating Sequences of Data Elements Using Cross-Attention Operations
Application:
18/102,985 →
Publication:
US US20230244907A1
Controlling Computing Devices Using Hierarchical Agents
Application:
18/105,180 →
Publication:
US US20240265264A1
Computer Code Generation from Task Descriptions Using Neural Networks
Allocating Computing Resources Between Model Size and Training Data During Training of a Machine Learning Model
Application:
18/127,551 →
Publication:
US US20230315532A1
Reinforcement Learning Using Distributed Prioritized Replay
Language Model for Processing a Multi-Mode Query Input
Using Automatically Uncovered Failure Cases to Improve the Performance of Neural Networks
Scene Understanding and Generation Using Neural Networks
Reinforcement Learning Using a Relational Network for Generating Data Encoding Relationships Between Entities in an Environment
Application:
18/168,123 →
Publication:
US US20230196146A1
Training Machine Learning Models by Determining Update Rules Using Neural Networks
Training a Speaker Neural Network Using One or More Listener Neural Networks
Controlling Agents Using Auxiliary Prediction Neural Networks That Generate State Value Estimates
Application:
18/230,056 →
Publication:
US US20240046070A1
Finding a Stationary Point of a Loss Function by an Iterative Algorithm Using a Variable Learning Rate Value
Application:
18/232,291 →
Publication:
US US20240054340A1
Reinforcement Learning Using Hindsight to Model Unpredictable Aspects of the Future
Application:
18/238,400 →
Publication:
US US20250068919A1
Predicting Exchange-Correlation Energies of Atomic Systems Using Neural Networks
Application:
18/260,182 →
Publication:
US US20240071577A1
Object-Based Prediction of Scene Transitions Using Neural Networks
Solving Mixed Integer Programs Using Neural Networks
Application:
18/267,363 →
Publication:
US US20240062060A1
Generating Neural Network Outputs by Enriching Latent Embeddings Using Self-Attention and Cross-Attention Operations
Application:
18/271,611 →
Publication:
US US20240104355A1
Predicting Complete Protein Representations from Masked Protein Representations
Application:
18/273,594 →
Publication:
US US20240087686A1
Sequence-To Sequence Neural Network Systems Using Look Ahead Tree Search
Application:
18/274,748 →
Publication:
US US20240104353A1
Determining Principal Components Using Multi-Agent Interaction
Application:
18/275,045 →
Publication:
US US20240086745A1
Generating Images Using Sparse Representations
Attention Neural Networks with Short-Term Memory Units
Application:
18/275,052 →
Publication:
US US20240095495A1
Neural Networks with Adaptive Gradient Clipping
Application:
18/275,087 →
Publication:
US US20240127586A1
Temporal Difference Scaling When Controlling Agents Using Reinforcement Learning
Application:
18/275,145 →
Publication:
US US20240104388A1
Rendering New Images of Scenes Using Geometry-Aware Neural Networks Conditioned on Latent Variables
Application:
18/275,332 →
Publication:
US US20240070972A1
Neural Network Reinforcement Learning with Diverse Policies
Application:
18/275,511 →
Publication:
US US20240104389A1
Controlling Agents Using State Associative Learning for Long-Term Credit Assignment
Application:
18/275,542 →
Publication:
US US20240086703A1
Imitation Learning Based on Prediction of Outcomes
Application:
18/275,722 →
Publication:
US US20240185082A1
Generating Differentiable Order Statistics Using Sorting Networks
Application:
18/275,737 →
Publication:
US US20240143696A1
Jointly Updating Agent Control Policies Using Estimated Best Responses to Current Control Policies
Application:
18/275,881 →
Publication:
US US20240046112A1
Predicting Protein Amino Acid Sequences Using Generative Models Conditioned on Protein Structure Embeddings
Application:
18/275,933 →
Publication:
US US20240120022A1
Nowcasting Using Generative Neural Networks
Application:
18/277,729 →
Publication:
US US20240176045A1
Continual Learning Neural Network System Training for Classification Type Tasks
Application:
18/278,473 →
Publication:
US US20240152749A1
Generating Output Signals Using Variable-Rate Discrete Representations
Application:
18/281,041 →
Publication:
US US20240144944A1
Reinforcement Learning Using an Ensemble of Discriminator Models
Application:
18/281,711 →
Publication:
US US20240311639A1
Training Graph Neural Networks Using a De-Noising Objective
Application:
18/283,131 →
Publication:
US US20240176982A1
Generating Neural Network Outputs by Cross Attention of Query Embeddings Over a Set of Latent Embeddings
Application:
18/284,595 →
Publication:
US US20240232580A1
Interactive Decoding of Words from Phoneme Score Distributions
Learning Diverse Skills for Tasks Using Sequential Latent Variables for Environment Dynamics
Application:
18/285,519 →
Publication:
US US20240185083A1
Multi-Objective Reinforcement Learning Using Weighted Policy Projection
Application:
18/286,504 →
Publication:
US US20240185084A1
Unsupervised Learning of Object Representations from Video Sequences Using Attention Over Space and Time
Autoregressively Generating Sequences of Data Elements Defining Actions to Be Performed by an Agent
Controlling Agents by Switching Between Control Policies During Task Episodes
Application:
18/294,784 →
Publication:
US US20240345873A1
Reinforcement and Imitation Learning for a Task
Selection-Inference Neural Network Systems
Data-Driven Robot Control
Jointly Learning Exploratory and Non-Exploratory Action Selection Policies
Application:
18/334,112 →
Publication:
US US20240028866A1
Data-Efficient Reinforcement Learning for Continuous Control Tasks
Training Generative Neural Networks Through Reinforced Self-Training
Application:
18/358,920 →
Publication:
US US20250036958A1
Recurrent Neural Networks for Data Item Generation
Application:
18/367,305 →
Publication:
US US20230419076A1
Discrete Token Processing Using Diffusion Models
Application:
18/374,447 →
Publication:
US US20240119261A1
Action Classification in Video Clips Using Attention-Based Neural Networks
Generating a Model of a Target Environment Based on Interactions of an Agent with Source Environments
Application:
18/379,988 →
Publication:
US US20240126945A1
Reinforcement Learning with Auxiliary Tasks
Application:
18/386,954 →
Publication:
US US20240144015A1
Training Neural Networks Through Reinforcement Learning Using Standardized Absolute Deviations
Application:
18/388,180 →
Publication:
US US20240169211A1
Selecting Reinforcement Learning Actions Using a Low-Level Controller
Patent:
12,367,391 →
Application:
18/398,046 →
Beam Search Decoding with Forward-Looking Scores
Planning Using a Jumpy Trajectory Decoder Neural Network
Application:
18/401,226 →
Publication:
US US20240220795A1
Reinforcement Learning Using Epistemic Value Estimation
Application:
18/405,988 →
Publication:
US US20240232642A1
Generating Images Using Neural Networks
Controlling Agents Using Amortized Q Learning
Application:
18/406,995 →
Publication:
US US20240160901A1
Using Hierarchical Representations for Neural Network Architecture Searching
Neural Population Learning
Application:
18/422,620 →
Publication:
US US20240412072A1
Training a Neural Network to Perform an Algorithmic Task Using a Self-Supervised Loss
Application:
18/423,239 →
Publication:
US US20240256879A1
Methods and Systems for Constrained Reinforcement Learning
Application:
18/424,437 →
Publication:
US US20240265263A1
Reinforcement Learning by Directly Learning an Advantage Function
Application:
18/424,520 →
Publication:
US US20240256882A1
Determining Stationary Points of a Loss Function Using Clipped and Unbiased Gradients
Application:
18/424,545 →
Publication:
US US20240256861A1
Reinforcement Learning Using Quantile Credit Assignment
Application:
18/424,561 →
Publication:
US US20240256883A1
Generating Environment Models Using in-Context Adaptation and Exploration
Application:
18/424,687 →
Publication:
US US20240256884A1
Controlling Agents Using Sub-Goals Generated by Language Model Neural Networks
Application:
18/443,285 →
Publication:
US US20240311617A1
Guided Dialogue Using Language Generation Neural Networks and Search
Controlling Agents Using Reporter Neural Networks
Application:
18/475,157 →
Publication:
US US20240112038A1
Meta-Learned Evolutionary Strategies Optimizer
Application:
18/475,859 →
Publication:
US US20240127071A1
Evaluating Representations with Read-Out Model Switching
Application:
18/475,972 →
Publication:
US US20240119302A1
Agent Control Through in-Context Reinforcement Learning
Application:
18/477,492 →
Publication:
US US20240104379A1
Progressive Neural Networks
Augmenting Attention-Based Neural Networks to Selectively Attend to Past Inputs
Distributed Training Using Actor-Critic Reinforcement Learning with Off-Policy Correction Factors
Multi-Task Neural Networks with Task-Specific Paths
Application:
18/487,707 →
Publication:
US US20240046106A1
Leveraging Offline Training Data and Agent Competency Measures to Improve Online Learning
Application:
18/492,415 →
Publication:
US US20240232643A9
Neural Programming
Continuous Control with Deep Reinforcement Learning
Generating Audio Using Neural Networks
Hierarchical Text Generation Using Language Model Neural Networks
Application:
18/527,211 →
Publication:
US US20240184982A1
Deep Reinforcement Learning with Fast Updating Recurrent Neural Networks and Slow Updating Recurrent Neural Networks
Application:
18/536,065 →
Publication:
US US20240220774A1
Learning Abstractions Using Patterns of Activations of a Neural Network Hidden Layer
Patent:
12,333,435 →
Application:
18/536,110 →
Gated Linear Networks
Application:
18/536,127 →
Publication:
US US20240202511A1
Reinforcement Learning by Solution of a Convex Markov Decision Process
Application:
18/558,894 →
Publication:
US US20240249151A1
Enhancing Population-Based Training of Neural Networks
Application:
18/562,180 →
Publication:
US US20240242091A1
Neural Networks with Hierarchical Attention Memory
Application:
18/564,959 →
Publication:
US US20240386264A1
Training Rate Control Neural Networks Through Reinforcement Learning
Multimodal Few-Shot Learning with Frozen Language Models
Adaptive Visual Speech Recognition
Controlling a Magnetic Field of a Magnetic Confinement Device Using a Neural Network
Application:
18/572,914 →
Publication:
US US20240312657A1
Training Agent Neural Networks Through Open-Ended Learning
Application:
18/577,484 →
Publication:
US US20240330701A1
Generating Predictions Characterizing Images Using Glimpses Extracted from the Images
Patent:
12,406,031 →
Application:
18/584,717 →
Animating Images Using Point Trajectories
Application:
18/600,552 →
Publication:
US US20240303897A1
Feedforward Generative Neural Networks
Multi-Stage Watermarking of a Digital Object Generated by a Machine Learning Model
Application:
18/611,417 →
Publication:
US US20240320529A1
Population Based Training of Neural Networks
Generating Discrete Latent Representations of Input Data Items
Application:
18/623,952 →
Publication:
US US20240354566A1
Programmable Reinforcement Learning Systems
Application:
18/637,279 →
Publication:
US US20240394504A1
Black-Box Optimization Using Neural Networks
Application:
18/639,686 →
Publication:
US US20240281714A1
Learning Observation Representations by Predicting the Future in Latent Space
Auto-Regressive Neural Network Systems with a Soft Attention Mechanism Using Support Data Patches
Action Selection Based on Environment Observations and Textual Instructions
Augmenting Machine Learning Language Models Using Search Engine Results
Training Action-Selection Neural Networks from Demonstrations Using Multiple Losses
Patent:
12,468,779 →
Application:
18/656,462 →
Reinforcement Learning Using Baseline and Policy Neural Networks
Application:
18/662,481 →
Publication:
US US20240362481A1
Verification of Agent Output Through Adversarial Debate
Application:
18/665,702 →
Publication:
US US20240386250A1
Generating Predictions for Non-Stationary Data Using Distributions Over Output Head Weights
Application:
18/666,682 →
Publication:
US US20240394516A1
Controlling Agents by Transferring Successor Features to New Tasks
Application:
18/668,080 →
Publication:
US US20240386281A1
Sequential Predictions Using Hierarchical Forecasting Models
Application:
18/668,101 →
Publication:
US US20240386334A1
Neural Networks for Scalable Continual Learning in Domains with Sequentially Learned Tasks
Application:
18/674,367 →
Publication:
US US20240394540A1
Gated Attention Neural Networks
Training a Neural Network to Predict Multi-Chain Protein Structures
Application:
18/694,204 →
Publication:
US US20240321386A1
Coordination of Multiple Robots Using Graph Neural Networks
Conformal Training of Machine- Learning Models
Application:
18/695,765 →
Publication:
US US20240394541A1
Demonstration-Driven Reinforcement Learning
Application:
18/698,218 →
Publication:
US US20240412063A1
Step-Unrolled Denoising Neural Networks
Application:
18/698,260 →
Publication:
US US20240412042A1
Retrieval Augmented Reinforcement Learning
Application:
18/698,890 →
Publication:
US US20240320506A1
Hierarchical Latent Mixture Policies for Agent Control
Application:
18/699,012 →
Publication:
US US20240403652A1
Designing Proteins by Jointly Modeling Sequence and Structure
Application:
18/703,737 →
Publication:
US US20250232841A1
Learned Computer Control Using Pointing Device and Keyboard Actions
Distributional Reinforcement Learning
Application:
18/754,726 →
Publication:
US US20240370707A1
Resolving Time-Delays Using Generative Models
Multi-Agent Reinforcement Learning with Matchmaking Policies
Classifying Input Examples Using a Comparison Set
Application:
18/780,270 →
Publication:
US US20250028931A1
Bandwidth Extension of Incoming Data Using Neural Networks
Application:
18/780,377 →
Publication:
US US20250022476A1
Rate Control Machine Learning Models with Feedback Control for Video Encoding
Application:
18/791,975 →
Publication:
US US20240397055A1
Training Neural Networks Using a Prioritized Experience Memory
Application:
18/805,367 →
Publication:
US US20250045583A1
Protein Structure Prediction from Amino Acid Sequences Using Self-Attention Neural Networks
Application:
18/813,386 →
Publication:
US US20240412809A1
Low-Level Feedback-Guided Scheduling for High-Level Synthesis
Application:
18/825,059 →
Publication:
US US20250094679A1
Optimizing Design Parameters Using a Simulation Neural Network
Application:
18/832,787 →
Publication:
US US20250103776A1
Local Cross-Attention Operations in Neural Networks
Application:
18/832,817 →
Publication:
US US20250103856A1
Generating Data Items Using Off-the-Shelf Guided Generative Diffusion Processes
Application:
18/834,184 →
Publication:
US US20250174000A1
Controlling Reinforcement Learning Agents Using Geometric Policy Composition
Application:
18/834,208 →
Publication:
US US20250124297A1
Agent Control Through Cultural Transmission
Application:
18/843,608 →
Publication:
US US20250209337A1
Generating Compressed Representations of Video for Efficient Learning of Video Tasks
Application:
18/844,744 →
Publication:
US US20250182453A1
Training Object Discovery Neural Networks and Feature Representation Neural Networks Using Self-Supervised Learning
Application:
18/844,798 →
Publication:
US US20250259068A1
Tracking Query Points in Videos Using Point Tracking Neural Networks
Application:
18/844,812 →
Publication:
US US20250191194A1
Processing Network Inputs Using Partitioned Attention
Application:
18/844,875 →
Publication:
US US20250181887A1
Hierarchical Reinforcement Learning at Scale
Application:
18/846,329 →
Publication:
US US20250200379A1
Reinforcement Learning to Explore Environments
Application:
18/846,412 →
Publication:
US US20250200380A1
Generating Output Sequences with Inline Evidence Using Language Model Neural Networks
Application:
18/846,910 →
Machine Learning Systems with Counterfactual Interventions
Application:
18/849,935 →
Publication:
US US20250209331A1
Exploration by Bootstrapped Prediction
Application:
18/850,206 →
Publication:
US US20250209338A1
Controlling Robots Using Latent Action Vector Conditioned Controller Neural Networks
Application:
18/850,857 →
Publication:
US US20250224737A1
Intra-Agent Speech to Facilitate Task Learning
Application:
18/851,177 →
Publication:
US US20250209340A1
Enhancing Images from a Mobile Device to Give a Professional Camera Effect
Application:
18/852,940 →
Publication:
US US20250252537A1
Epistemic Machine Learning Models
Application:
18/856,200 →
Publication:
US US20250245499A1
Data Compression and Reconstruction Using Sparse Meta-Learned Neural Networks
Application:
18/862,782 →
Publication:
US US20250356175A1
Negotiating Contracts for Agent Cooperation in Multi-Agent Systems
Application:
18/864,639 →
Publication:
US US20250335244A1
Variable Resolution Variable Frame Rate Video Coding Using Neural Networks
Application:
18/864,656 →
Publication:
US US20250310561A1
Determining Generalized Eigenvectors Using Multi-Agent Interactions
Application:
18/867,043 →
Publication:
US US20250335538A1
Contrastive Learning Using Positive Pseudo Labels
Application:
18/867,073 →
Publication:
US US20250342355A1
System and Method for Reinforcement Learning Based on Prior Trajectories
Application:
18/867,094 →
Publication:
US US20250348748A1
Resource Navigation Using Neural Networks
Large-Scale Retrieval Augmented Reinforcement Learning
Learning Tasks Using Skill Sequencing for Temporally-Extended Exploration
Application:
18/867,874 →
Publication:
US US20250348749A1
Simulating Physical Environments Using Fine-Resolution and Coarse-Resolution Meshes
Application:
18/868,017 →
Publication:
US US20250181803A1
Automated Discovery of Agents in Systems
Application:
18/872,327 →
Publication:
US US20250356161A1
Reinforcement Learning Using Density Estimation with Online Clustering for Exploration
Application:
18/872,611 →
Neural Networks with Regularized Attention Layers
Application:
18/872,883 →
Publication:
US US20250307603A1
Graph Neural Networks That Model Face-Face Interactions Between Meshes
Application:
18/873,202 →
Training Camera Policy Neural Networks Through Self-Prediction
Application:
18/874,849 →
Publication:
US US20250365502A1
Simulating Physical Environments with Discontinuous Dynamics Using Graph Neural Networks
Application:
18/874,871 →
Publication:
US US20250371223A1
Verifying the Provenance of a Digital Object Using Watermarking and Embeddings
Application:
18/886,685 →
Publication:
US US20250087221A1
Verifying the Provenance of a Digital Object Using Watermarking and Embeddings
Application:
18/886,824 →
Publication:
US US20250149048A1
Generating Suggested Communications by Simulating Interactions Using Language Model Neural Networks
Application:
18/892,217 →
Publication:
US US20250094676A1
Training a High-Level Controller to Generate Natural Language Commands for Controlling an Agent
Application:
18/892,260 →
Publication:
US US20250093828A1
Autoregressive Neural Networks for the Generation of Polygonal Meshes of 3D Objects
Application:
18/901,976 →
Publication:
US US20250131236A1
Generating Output Examples Using Recurrent Neural Networks Conditioned on Bit Values
Application:
18/912,978 →
Publication:
US US20250117652A1
Training Action Selection Neural Networks Using Look-Ahead Search
Rating Tasks and Policies Using Conditional Probability Distributions Derived from Equilibrium-Based Solutions of Games
Application:
18/919,257 →
Publication:
US US20250032936A1
Composable Function-Preserving Expansions of Neural Networks
Application:
18/924,844 →
Publication:
US US20250131254A1
Training an Unsupervised Memory-Based Prediction System to Learn Compressed Representations of an Environment
Application:
18/929,321 →
Publication:
US US20250051289A1
Machine Learning for Determining Protein Structures
Application:
18/940,983 →
Publication:
US US20250069705A1
Unsupervised Learning of Object Keypoint Locations in Images Through Temporal Transport or Spatio-Temporal Transport
Application:
18/945,375 →
Publication:
US US20250182439A1
Reinforcement Learning for Active Sequence Processing
Application:
18/953,004 →
Publication:
US US20250148774A1
Fast Exploration and Learning of Latent Graph Models
Training Action Selection Neural Networks Using Off-Policy Actor Critic Reinforcement Learning and Stochastic Dueling Neural Networks
Application:
18/962,266 →
Publication:
US US20250094772A1
Learned Computer Control Using Pointing Device and Keyboard Actions
Application:
18/967,935 →
Publication:
US US20250093970A1
Distributional Reinforcement Learning Using Quantile Function Neural Networks
Application:
18/981,840 →
Publication:
US US20250117654A1
Adaptive Visual Speech Recognition
Application:
18/986,673 →
Publication:
US US20250232762A1
Privacy-Sensitive Neural Network Training Using Data Augmentation
Application:
18/141,273 →
Publication:
US US20230351042A1
Scalable and Compressive Neural Network Data Storage System
Step-Unrolled Denoising Neural Networks
Application:
19/051,041 →
Publication:
US US20250181897A1
Machine Learning Systems with Memory Based Parameter Adaptation for Learning Fast and Slower
Application:
19/053,774 →
Publication:
US US20250190758A1
Action Classification in Video Clips Using Attention-Based Neural Networks
Application:
19/053,815 →
Publication:
US US20250285441A1
Neural Programming
Application:
19/061,843 →
Publication:
US US20250292080A1
Persisting and Restoring in-Memory Neighbor Graph Vector Indexes
Application:
19/063,012 →
Publication:
US US20260072924A1
Selection-Inference Neural Network Systems
Application:
19/107,903 →
Associative Long Short-Term Memory Neural Network Layers
PCT:
PCT/US2016/069505 ↗
Augmenting Neural Networks with External Memory
PCT:
PCT/US2016/069570 ↗
Progressive Neural Networks
PCT:
PCT/US2016/069589 ↗
Compressing Images Using Neural Networks
PCT:
PCT/US2016/069606 ↗
Generating Images Using Neural Networks
PCT:
PCT/US2017/014990 ↗
Augmenting Neural Networks with Sparsely-Accessed External Memory
PCT:
PCT/US2017/016415 ↗
Generative Neural Networks
PCT:
PCT/US2017/016594 ↗
Reinforcement Learning Using Pseudo-Counts
PCT:
PCT/US2017/033218 ↗
Model-Free Control for Reinforcement Learning Agents
PCT:
PCT/US2017/033221 ↗
Classifying Input Examples Using a Comparison Set
PCT:
PCT/US2017/033604 ↗
Training Neural Networks Using Synthetic Gradients
PCT:
PCT/US2017/033697 ↗
Memory-Efficient Backpropagation Through Time
PCT:
PCT/US2017/033698 ↗
Interaction Networks
PCT:
PCT/US2017/033702 ↗
Training Machine Learning Models
PCT:
PCT/US2017/033703 ↗
Training Machine Learning Models on Multiple Machine Learning Tasks
PCT:
PCT/US2017/042542 ↗
Generating Audio Using Neural Networks
PCT:
PCT/US2017/050320 ↗
Processing Sequences Using Convolutional Neural Networks
PCT:
PCT/US2017/050335 ↗
Generating Video Frames Using Neural Networks
PCT:
PCT/US2017/054528 ↗
Neural Networks for Selecting Actions to Be Performed by a Robotic Agent
PCT:
PCT/US2017/055894 ↗
Parallel Execution of Gated Activation Unit Operations
PCT:
PCT/US2017/057611 ↗
Parallel Processing for Signal Generation Neural Networks
PCT:
PCT/US2017/057663 ↗
Processing Text Sequences Using Neural Networks
PCT:
PCT/US2017/058046 ↗
Dynamic Placement of Computation Sub-Graphs
PCT:
PCT/US2018/015896 ↗
Contiguous Sparsity Pattern Neural Networks
PCT:
PCT/US2019/017495 ↗
Speech Synthesis Utilizing Audio Waveform Difference Signal(S)
PCT:
PCT/US2019/033104 ↗
Image Generation Using Subscaling and Depth Up-Scaling
PCT:
PCT/US2019/053666 ↗
Related Assignments
(25)
Other recorded transfers of the patents in this record — the chain of ownership.
Assignment of Assignor's Interest
Dec 20, 2018
From: BLUNDELL, CHARLES; URIA-MARTINEZ, BENIGNO
To: GOOGLE INC.
Reel/Frame 047835/0255 →
Assignment of Assignor's Interest
Dec 20, 2018
From: GOOGLE INC.
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 047835/0366 →
Assignment of Assignor's Interest
Dec 21, 2018
From: BATTAGLIA, PETER WILLIAM; PASCANU, RAZVAN
To: GOOGLE INC.
Reel/Frame 047840/0292 →
Assignment of Assignor's Interest
Dec 21, 2018
From: GOOGLE INC.
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 047840/0366 →
Assignment of Assignor's Interest
Mar 27, 2019
From: DESJARDINS, GUILLAUME; PASCANU, RAZVAN; HADSELL, RAIA THAIS; KIRKPATRICK, JAMES
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 048710/0397 →
Assignment of Assignor's Interest
Mar 6, 2020
From: JUMPER, JOHN; SENIOR, ANDREW W.; EVANS, RICHARD ANDREW; GOUWS, STEPHAN
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 052041/0183 →
Assignment of Assignor's Interest
Mar 23, 2020
From: LI, YUJIA; NAIR, VINOD; GIMENO GIL, FELIX AXEL; PALIWAL, ADITYA
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 052198/0392 →
Assignment of Assignor's Interest
Jun 9, 2020
From: SPRECHMANN, PABLO; JAYAKUMAR, SIDDHANT; RAE, JACK WILLIAM; PRITZEL, ALEXANDER
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 052884/0180 →
Assignment of Assignor's Interest
Jun 19, 2020
From: SUNEHAG, PETER GORAN
To: GOOGLE INC.
Reel/Frame 052987/0945 →
Assignment of Assignor's Interest
Jun 19, 2020
From: GOOGLE INC.
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 052988/0001 →
Assignment of Assignor's Interest
Aug 11, 2020
From: GANIN, IAROSLAV; KULKARNI, TEJAS DATTATRAYA; VINYALS, ORIOL; ESLAMI, SEYED MOHAMMADALI
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 053461/0334 →
Assignment of Assignor's Interest
Sep 1, 2020
From: RAMALHO, TIAGO MIGUEL SARGENTO PIRES; ROSENBAUM, DAN; GARNELO, MARTA; MADDISON, CHRISTOPHER
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 053656/0494 →
Assignment of Assignor's Interest
Sep 2, 2020
From: SHILLINGFORD, BRENDAN; FOERSTER, JAKOB NICOLAUS
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 053676/0226 →
Assignment of Assignor's Interest
Oct 12, 2020
From: PFAU, DAVID BENJAMIN; SPENCER, JAMES; MATTHEWS, ALEXANDER GRAEME DE GARIS
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 054030/0449 →
Assignment of Assignor's Interest
Oct 13, 2020
From: BINKOWSKI, MIKOLAJ; SIMONYAN, KAREN; DONAHUE, JEFFREY; CLARK, AIDAN
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 054033/0347 →
Assignment of Assignor's Interest
Oct 19, 2020
From: ZHENG, ZEYU; OH, JUNHYUK; BAVEJA, SATINDER SINGH
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 054098/0522 →
Assignment of Assignor's Interest
Nov 2, 2020
From: JEONG, RAE CHAN; AYTAR, YUSUF; KHOSID, DAVID; ZHOU, YUXIANG
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 054243/0504 →
Assignment of Assignor's Interest
Nov 10, 2020
From: GOOGLE INC.
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 054327/0677 →
Assignment of Assignor's Interest
Nov 10, 2020
From: GRAVES, ALEXANDER BENJAMIN; DANIHELKA, IVO; HARLEY, TIMOTHY JAMES ALEXANDER; REYNOLDS, MALCOLM KEVIN CAMPBELL
To: GOOGLE INC.
Reel/Frame 054327/0234 →
Assignment of Assignor's Interest
Jan 25, 2021
From: WIERSTRA, DANIEL PIETER; LI, YUJIA; PASCANU, RAZVAN; BATTAGLIA, PETER WILLIAM
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 055024/0503 →
Assignment of Assignor's Interest
Jan 27, 2021
From: GENDRON-BELLEMARE, MARC; MENICK, JACOB LEE; GRAVES, ALEXANDER BENJAMIN; KAVUKCUOGLU, KORAY
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 055052/0044 →
Assignment of Assignor's Interest
Jan 28, 2021
From: GENDRON-BELLEMARE, MARC; MENICK, JACOB LEE; GRAVES, ALEXANDER BENJAMIN; KAVUKCUOGLU, KORAY
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 055060/0221 →
Assignment of Assignor's Interest
Feb 1, 2021
From: PFAU, DAVID BENJAMIN; PETERSEN, STIG; AGARWAL, ASHISH; BARRETT, DAVID
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 055101/0223 →
Assignment of Assignor's Interest
Feb 1, 2021
From: RIEDMILLER, MARTIN; HADSELL, RAIA THAIS; BATTAGLIA, PETER WILLIAM; MEREL, JOSHUA
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 055100/0531 →
Assignment of Assignor's Interest
May 21, 2021
From: SONG, HASUK; TACCHETTI, ANDREA; BATTAGLIA, PETER WILLIAM; ZAMBALDI, VINICIUS
To: DEEPMIND TECHNOLOGIES LIMITED
Reel/Frame 056313/0347 →