Patents by Inventor Philip RODGERS

Philip RODGERS has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20250086474
    Abstract: Collaborative training with buffered activations is performed by partitioning a plurality of layers of a neural network model into a device partition and a server partition; transmitting, to a computation device, the device partition, training, collaboratively with the computation device through a network, the neural network model by applying the server partition to a set of activations to obtain a set of output instances, the set of activations obtained by one of receiving, from the computation device, the set of activations as output from the device partition, or reading, from an activation buffer, the set of activations as previously recorded, applying a loss function relating activations to output instances to each output instance among the current set of output instances to obtain a set of loss values, and computing a set of gradient vectors for each layer of the server partition based on the set of loss values.
    Type: Application
    Filed: December 21, 2022
    Publication date: March 13, 2025
    Inventors: Di WU, Blesson VARGHESE, Philip RODGERS, Rehmat ULLAH, Peter KILPATRICK, Ivor SPENCE
  • Publication number: 20250086483
    Abstract: Edge-masking guided node pruning is performed by masking at least one edge among a plurality of edges of a trained model to produce a masked model, initializing the masked model, training the masked model, detecting, from among a plurality of channels of the masked model, each channel among the plurality of channels including a set of edges among the plurality of edges, at least one zero channel in which each edge among the set of edges is masked; determining, from among a plurality of nodes of the masked model, each node corresponding to two channels among the plurality of channels, at least one removable node in which the corresponding two channels are zero channels; and pruning the masked model to remove the removable nodes from the masked model, resulting in a pruned model.
    Type: Application
    Filed: December 21, 2022
    Publication date: March 13, 2025
    Inventors: Bailey ECCLES, Blesson VARGHESE, Philip RODGERS, Peter KILPATRICK, Ivor SPENCE
  • Publication number: 20250077887
    Abstract: Collaborative training with compressed transmissions is performed by partitioning a plurality of layers of a neural network model into a device partition and a server partition, combining a plurality of encoding layers of an auto-encoder neural network with the device partition, wherein a largest encoding layer among the plurality of encoding layers is adjacent a layer of the device partition bordering the server partition, combining a plurality of decoding layers of the auto-encoder neural network with the server partition, wherein a largest decoding layer among the plurality of decoding layers is adjacent a layer of the server partition bordering the device partition, transmitting, to a computation device, the device partition combined with the plurality of encoding layers, and training, collaboratively with the computation device through a network, the neural network model.
    Type: Application
    Filed: December 12, 2022
    Publication date: March 6, 2025
    Inventors: Di WU, Blesson VARGHESE, Philip RODGERS, Rehmat ULLAH, Peter KILPATRICK, Ivor SPENCE
  • Publication number: 20240427611
    Abstract: Software controllers are generated and applied by identifying a controllable parameter and a readable metric from a target entity, generating a software controller configured to determine a value of the controllable parameter based on the readable metric, receiving a first metric value corresponding to the readable metric, and applying a first controllable parameter value to the target entity, the first controllable parameter value produced by the software controller in response to input of the first metric value. Software controllers are generated by arranging a sequence of operations relating the controllable parameter to the readable metric, applying a plurality of genetic operators to the sequence to produce a plurality of offspring sequences, and determining whether each offspring sequence among the plurality of offspring sequences is fit for use as the software controller.
    Type: Application
    Filed: December 8, 2022
    Publication date: December 26, 2024
    Inventors: Damien ANDERSON, Paul HARVEY, Yusaku KANETA, Petros PAPADOPOULOS, Philip RODGERS, Marc ROPER
  • Publication number: 20240394555
    Abstract: Neural networks are collaboratively trained with parallel operations by performing operations in a plurality of consecutive time periods including a first plurality of consecutive time periods during which the server receives a set of activations, applies the server partition to a set of activations, applies a set of output instances to a loss function, and computes a set of gradient vectors, and a second plurality of consecutive time periods during which the server transmits a set of gradient vectors.
    Type: Application
    Filed: November 11, 2022
    Publication date: November 28, 2024
    Inventors: Zihan ZHANG, Blesson VARGHESE, Philip RODGERS, Ivor SPENCE, Peter KILPATRICK
  • Publication number: 20240069982
    Abstract: A method of workload management in a Kubernetes (K8s) environment may include obtaining, by a digital twin (DT) representing a cluster state, performance data of at least one K8s cluster, generating, by the DT, a behavioral model based on the performance data, determining, by a horizontal pod autoscaler (HPA) controller, a HPA configuration based on the behavioral model and implementing, by an HPA of the at least one K8s cluster, the determined HPA configuration
    Type: Application
    Filed: June 5, 2023
    Publication date: February 29, 2024
    Applicants: RAKUTEN SYMPHONY, INC., TECHNICAL UNIVERSITY OF MUNICH
    Inventors: Johannes Peter Donato ZERWAS, Patrick Michael KRÄMER, Wolfgang Leonhard KELLERER, Navidreza ASADI, Razvan-Mihai URSU, Philip RODGERS, Jee Chang Leon WONG