公开(公告)号：US20240289639A1

公开(公告)日：2024-08-29

申请号：US18113350

申请日：2023-02-23

Applicant: Substrate Artificial Intelligence SA

Inventor： James Brennan WORTH

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: A method includes receiving information associated with interactions of an agent with an environment according to a policy defined based on a plurality of hyperparameters. The interactions can include states associated with the environment and actions associated with each state. The method includes receiving an indication of a target state to be achieved by the agent in the environment and determining an indication of a set of current values. Each current value from the set of current values is associated with a different hyperparameter from the plurality of hyperparameters. The plurality of hyperparameters can impact the agent's interactions with the environment. The method includes modifying the policy by changing a current value from the set of current values based on the information associated with the interactions of the agent with the environment and the indication of the target state to increase a likelihood of the agent achieving the target state.

公开(公告)号：US12056585B2

公开(公告)日：2024-08-06

申请号：US17110275

申请日：2020-12-02

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Evelyn Duesterwald ,  Anupama Murthi ,  Michael Hind ,  Matthew Richard Arnold ,  Benjamin Tyler Elder ,  Jiri Navratil

IPC: G06N20/00 ,  G06N5/04 ,  G06N3/0985

CPC classification number: G06N20/00 ,  G06N5/04 ,  G06N3/0985

Abstract: A computer implemented method of performing large-scale machine learning experiments includes expanding on one or more input datasets by systematically generating several data set drift splits. A set of experimental jobs corresponding to the generated data set drift splits are executed to generate experimental results. The experimental results are processed, consolidated, and clustered according to the generated data set drift splits.

公开(公告)号：US20240160949A1

公开(公告)日：2024-05-16

申请号：US18454329

申请日：2023-08-23

Applicant: Tata Consultancy Services Limited

Inventor： Shruti Kunal KUNDE ,  Rekha SINGHAL ,  Varad Anant PIMPALKHUTE

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: Technical limitation of conventional Gradient-Based Meta Learners is their inability to adapt to scenarios where input tasks are sampled from multiple distributions. Training multiple models, with one model per distribution adds to the training time owing to increased compute. A method and system for generating meta-subnets for efficient model generalization in a multi-distribution scenario using Binary Mask Perceptron (BMP) technique or a Multi-modal Meta Supermasks (MMSUP) technique is provided. The BMP utilizes an adaptor which determines a binary mask, thus training only those layers which are relevant for given input distribution, leading to improved training accuracy in a cross-domain scenario. The MMSUP, further determines relevant subnets for each input distribution, thus, generalizing well as compared to standard MAML. The BMP and MMSUP, beat Multi-MAML in terms of training time as they train a single model on multiple distributions as opposed to Multi-MAML which trains multiple models.

公开(公告)号：US20240119308A1

公开(公告)日：2024-04-11

申请号：US18159036

申请日：2023-01-24

Applicant: Salesforce, Inc.

Inventor： Arundhati Banerjee ,  Stephan Zheng ,  Soham Phade ,  Stefano Ermon

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: Embodiments provide a method for predicting agent actions for neural network based agents according to an intervention. The method includes obtaining a first agent action at a first time step and a first intervention generated according to an intervention policy. The method also includes generating, by the neural network based agent model, a predicted agent action conditioned on the first agent action and the first intervention. The method also includes generating, by a neural network based intervention model, a second intervention according to the intervention policy and conditioned on the first agent action, the first intervention, and the predicted agent action. The method further includes executing a second agent action according to an agent policy that incurs a reward based on the second intervention. The method further includes training the neural network based intervention model by updating parameters of the neural network based intervention model based on an expected return.

公开(公告)号：US20230359863A1

公开(公告)日：2023-11-09

申请号：US18022468

申请日：2021-08-23

Applicant: David Alvord ,  David I. Pendleton ,  Aimee N. Williams ,  Georgia Tech Research Corporation

Inventor： David Alvord ,  David I. Pendleton ,  Aimee N. Williams

IPC: G06N3/045 ,  G01M15/14 ,  F02K9/96 ,  G06N3/0985

CPC classification number: G06N3/045 ,  F02K9/96 ,  G01M15/14 ,  G06N3/0985 ,  F05D2260/83

Abstract: An exemplary virtual sensing method and system are disclosed for predictive reliability (VIPR) procedure and/or controls that employ artificial intelligence and machine learning (AI/ML), particularly deep neural networks and multi-modal deep learning, with vehicle sensor data to create virtual sensors. The virtual sensors can be used to estimate measurements and operating conditions in a hostile environment in rockets and vehicle systems.

公开(公告)号：US20230196122A1

公开(公告)日：2023-06-22

申请号：US17899913

申请日：2022-08-31

Applicant: NEC Laboratories America, Inc.

Inventor： Yumin Suh ,  Samuel Schulter ,  Xiang Yu ,  Masoud Faraki ,  Manmohan Chandraker ,  Dripta Raychaudhuri

IPC: G06N3/0985

CPC classification number: G06N3/0985

Abstract: Systems and methods for generating a hypernetwork configured to be trained for a plurality of tasks; receiving a task preference vector identifying a hierarchical priority for the plurality of tasks, and a resource constraint as a tuple; finding tree sub-structures and the corresponding modulation of features for every tuple within an N-stream anchor network; optimizing a branching regularized loss function to train an edge hypernet; and training a weight hypernet, keeping the anchor net and the edge hypernet fixed.

公开(公告)号：US20240330701A1

公开(公告)日：2024-10-03

申请号：US18577484

申请日：2022-07-27

Applicant: DeepMind Technologies Limited

Inventor： Maxwell Elliot Jaderberg ,  Wojciech Czarnecki

IPC: G06N3/092 ,  G06N3/0985

CPC classification number: G06N3/092 ,  G06N3/0985

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for raining an agent neural network for use in controlling an agent to perform a plurality of tasks. One of the methods includes maintaining population data specifying a population of one or more candidate agent neural networks; and training each candidate agent neural network on a respective set of one or more tasks to update the parameter values of the parameters of the candidate agent neural networks in the population data, the training comprising, for each candidate agent neural network: obtaining data identifying a candidate task; obtaining data specifying a control policy for the candidate task; determining whether to train the candidate agent neural network on the candidate task; and in response to determining to train the candidate agent neural network on the candidate task, training the candidate agent neural network on the candidate task.

公开(公告)号：US12099933B2

公开(公告)日：2024-09-24

申请号：US17081710

申请日：2020-10-27

Applicant: EMC IP Holding Company LLC

Inventor： Pablo Nascimento da Silva ,  Paulo Abelha Ferreira ,  Tiago Salviano Calmon ,  Roberto Nery Stelling Neto ,  Vinicius Michel Gottin

IPC: G06N3/098 ,  G06N3/08 ,  G06N3/082 ,  G06N3/0985 ,  G06N20/00 ,  G06N20/20

CPC classification number: G06N3/098 ,  G06N3/082 ,  G06N3/0985 ,  G06N20/00 ,  G06N3/08 ,  G06N20/20

Abstract: A framework for rapidly prototyping federated learning algorithms. Specifically, the disclosed framework proposes a method and system for evaluating different hypotheses for configuring learning model, which may be optimized through federated learning. Through the disclosed framework, these hypotheses may be tested for scalability, hardware and network resource performance, as well as for new learning state compression and/or aggregation technique effectiveness. Further, these hypotheses may be tested through federated learning simulations, which avoid costs associated with deploying these hypotheses to be tested across production systems.

公开(公告)号：US20240303475A1

公开(公告)日：2024-09-12

申请号：US18667699

申请日：2024-05-17

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Chenchen YANG ,  Hang ZHANG ,  Xu LI ,  Bidi YING

IPC: G06N3/0475 ,  G06N3/0985

CPC classification number: G06N3/0475 ,  G06N3/0985

Abstract: A method of privacy protection includes receiving from a service customer, a service request requesting for a service of privacy protection. A generative model is used to generate synthetic data based on the service request and the synthetic data is provided to a discriminator. The discriminator performs a comparison between data from the service customer and the received synthetic data, and providing a result of the comparison to the generator, where privacy of the service customer is included in or inferred from the data from the service customer. Based on the result of the comparison from the discriminator, the generator updates the generative model until the generated synthetic data meets a preconfigured requirement. Each time the generative model is updated, newly updated synthetic data is provide to the discriminator. Once the preconfigured requirement is met, the latest synthetic data or the latest generative model is provided to a data consumer.

公开(公告)号：US20240194341A1

公开(公告)日：2024-06-13

申请号：US18503486

申请日：2023-11-07

Applicant: Dexcom, Inc.

Inventor： Joost Herman VAN DER LINDEN ,  Mark DERDZINSKI ,  Margaret A. CRAWFORD ,  Giada ACCIAROLI ,  Christopher R. HANNEMANN

IPC: G16H50/20 ,  G06N3/0985

CPC classification number: G16H50/20 ,  G06N3/0985

Abstract: Systems, devices, and methods for determining user-specific hyperparameters for decision support models are provided. In one embodiment, a non-transitory computer readable storage medium storing a program is provided, the program comprising instructions that, when executed by at least one processor of a computing device, cause the at least one processor to perform operations including performing an initial exploration phase; performing a training phase; and performing an exploration-exploitation phase by: dividing users into an exploration subset and an exploitation subset; determining at least one optimal hyperparameter for each user of the exploitation subset; determining, using the at least one optimal hyperparameter, at least one decision support output for each user of the exploitation subset; randomly assigning at least one hyperparameter to each user of the exploration subset; and determining, using the at least one randomly assigned hyperparameter, at least one decision support output for each user of the exploration subset.