Patents by Inventor David Moloney

David Moloney 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: 20200098096
    Abstract: Examples to selectively generate a masked image include: a convolutional neural network detector to detect a first feature and a second feature in an image captured by a camera; a feature recognizer to determine the first feature is a displayable feature and the second feature is a non-displayable feature by comparing the first and second features of the image to reference feature images stored in a memory; and a blur generator to generate the masked image to display the displayable feature and mask the non-displayable feature.
    Type: Application
    Filed: September 24, 2018
    Publication date: March 26, 2020
    Inventor: David Moloney
  • Publication number: 20200089506
    Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve convolution efficiency of a convolution neural network (CNN) accelerator. An example hardware accelerator includes a hardware data path element (DPE) in a DPE array, the hardware DPE including an accumulator, and a multiplier coupled to the accumulator, the multiplier to multiply first inputs including an activation value and a filter coefficient value to generate a first convolution output when the hardware DPE is in a convolution mode, and a controller coupled to the DPE array, the controller to adjust the hardware DPE from the convolution mode to a pooling mode by causing at least one of the multiplier or the accumulator to generate a second convolution output based on second inputs, the second inputs including an output location value of a pool area, at least one of the first inputs different from at least one of the second inputs.
    Type: Application
    Filed: November 18, 2019
    Publication date: March 19, 2020
    Inventors: Sean Power, David Moloney, Brendan Barry, Fergal Connor
  • Patent number: 10574890
    Abstract: An example mobile camera includes a first convolutional neural network to recognize a first feature in first sensor data in response to the first feature being detected in the first sensor data; a state transitioner to transition the mobile camera from a first feature detection state to a second feature detection state in response to the first convolutional neural network recognizing the first feature, the mobile camera to operate using higher power consumption in the second feature detection state than in the first feature detection state; a second convolutional neural network to recognize a second feature in second sensor data in the second feature detection state; and a communications interface to send to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.
    Type: Grant
    Filed: January 12, 2018
    Date of Patent: February 25, 2020
    Assignee: Movidius Ltd.
    Inventors: David Moloney, Alireza Dehghani
  • Patent number: 10572252
    Abstract: A vector processor is disclosed including a variety of variable-length instructions. Computer-implemented methods are disclosed for efficiently carrying out a variety of operations in a time-conscious, memory-efficient, and power-efficient manner. Methods for more efficiently managing a buffer by controlling the threshold based on the length of delay line instructions are disclosed. Methods for disposing multi-type and multi-size operations in hardware are disclosed. Methods for condensing look-up tables are disclosed. Methods for in-line alteration of variables are disclosed.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: February 25, 2020
    Assignee: Movidius Limited
    Inventors: Brendan Barry, Fergal Connor, Martin O'Riordan, David Moloney, Sean Power
  • Publication number: 20200013265
    Abstract: Example methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement video surveillance with neural networks are disclosed. Example systems disclosed herein include a database to store records of operator-labeled video segments (e.g., as records of operator-labeled video segments). The operator-labeled video segments include reference video segments and corresponding reference event labels describing the video segments. Disclosed example systems also include a neural network including a first instance of an inference engine, and a training engine to train the first instance of the inference engine based on a training set of the operator-labeled video segments obtained from the database, the first instance of the inference engine to infer events from the operator-labeled video segments included in the training set.
    Type: Application
    Filed: July 5, 2018
    Publication date: January 9, 2020
    Inventor: David Moloney
  • Patent number: 10521238
    Abstract: The present application discloses a computing device that can provide a low-power, highly capable computing platform for computational imaging. The computing device can include one or more processing units, for example one or more vector processors and one or more hardware accelerators, an intelligent memory fabric, a peripheral device, and a power management module. The computing device can communicate with external devices, such as one or more image sensors, an accelerometer, a gyroscope, or any other suitable sensor devices.
    Type: Grant
    Filed: February 20, 2018
    Date of Patent: December 31, 2019
    Assignee: Movidius Limited
    Inventors: Brendan Barry, Richard Richmond, Fergal Connor, David Moloney
  • Publication number: 20190370005
    Abstract: The present application relates generally to a parallel processing device. The parallel processing device can include a plurality of processing elements, a memory subsystem, and an interconnect system. The memory subsystem can include a plurality of memory slices, at least one of which is associated with one of the plurality of processing elements and comprises a plurality of random access memory (RAM) tiles, each tile having individual read and write ports. The interconnect system is configured to couple the plurality of processing elements and the memory subsystem. The interconnect system includes a local interconnect and a global interconnect.
    Type: Application
    Filed: June 18, 2019
    Publication date: December 5, 2019
    Inventors: David Moloney, Richard Richmond, David Donohoe, Brendan Barry
  • Publication number: 20190340464
    Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.
    Type: Application
    Filed: February 8, 2019
    Publication date: November 7, 2019
    Inventors: David MOLONEY, Alireza DEHGHANI
  • Patent number: 10460704
    Abstract: Systems and methods are provided for rendering of a dual eye-specific display. The system tracks the user's eye movements and/or positions, in some implementations, based on electroencephalography (EEG) of the user, to correctly label the central (foveal) and peripheral (extra-foveal) areas of the display. Foveal data is fully rendered while extra-foveal data is reduced in resolution and, in some implementations, shared between the two displays.
    Type: Grant
    Filed: April 1, 2016
    Date of Patent: October 29, 2019
    Assignee: Movidius Limited
    Inventors: Brendan Barry, David Moloney
  • Publication number: 20190279082
    Abstract: An example includes sending first weight values to first client devices; accessing sets of updated weight values provided by the first client devices, the updated weight values generated by the first client devices training respective first convolutional neural networks (CNNs) based on: the first weight values, and sensor data generated at the client devices; testing performance in a second CNN of at least one of: the sets of the updated weight values, or a combination of ones of the updated weight values from the sets of the updated weight values; selecting server-synchronized weight (SSW) values from the at least one of: the sets of the updated weight values, or a combination of ones of the updated weight values from the sets of the updated weight values; and sending the SSW values to at least one of: at least some of the first client devices, or second client devices.
    Type: Application
    Filed: March 7, 2018
    Publication date: September 12, 2019
    Inventors: David Moloney, Alireza Dehghani, Aubrey Keith Dunne
  • Patent number: 10360040
    Abstract: The present application relates generally to a parallel processing device. The parallel processing device can include a plurality of processing elements, a memory subsystem, and an interconnect system. The memory subsystem can include a plurality of memory slices, at least one of which is associated with one of the plurality of processing elements and comprises a plurality of random access memory (RAM) tiles, each tile having individual read and write ports. The interconnect system is configured to couple the plurality of processing elements and the memory subsystem. The interconnect system includes a local interconnect and a global interconnect.
    Type: Grant
    Filed: February 20, 2018
    Date of Patent: July 23, 2019
    Assignee: Movidius, LTD.
    Inventors: David Moloney, Richard Richmond, David Donohoe, Brendan Barry
  • Publication number: 20190222756
    Abstract: An example mobile camera includes a first convolutional neural network to recognize a first feature in first sensor data in response to the first feature being detected in the first sensor data; a state transitioner to transition the mobile camera from a first feature detection state to a second feature detection state in response to the first convolutional neural network recognizing the first feature, the mobile camera to operate using higher power consumption in the second feature detection state than in the first feature detection state; a second convolutional neural network to recognize a second feature in second sensor data in the second feature detection state; and a communications interface to send to an external device at least one of first metadata corresponding to the first feature or second metadata corresponding to the second feature.
    Type: Application
    Filed: January 12, 2018
    Publication date: July 18, 2019
    Inventors: David Moloney, Alireza Dehghani
  • Publication number: 20190156141
    Abstract: Methods, systems, apparatus and articles of manufacture are disclosed herein to improve image classification with boundary-bitmaps. An example disclosed apparatus includes a silhouette engine to identify a foreground silhouette within the image, generate a bounding box based on borders of the foreground silhouette, and generate an encoded silhouette matrix which identifies cells of a foreground and cells of a background, a convolution cell selector to convolve the encoded silhouette matrix to generate a convoluted bitmap matrix, and a filter cell selector to improve image classification efficiency by identifying eligible blocks of the convoluted bitmap matrix by retaining first respective cells of the convoluted bitmap matrix that satisfy a cell retention threshold, and removing second respective cells of the convoluted bitmap matrix that do not satisfy the cell retention threshold.
    Type: Application
    Filed: June 6, 2017
    Publication date: May 23, 2019
    Applicant: Linear Algebra Technologies Limited
    Inventors: David Moloney, Alireza Dehghani
  • Publication number: 20190136767
    Abstract: An improved system, apparatus and method may be configured for detecting coking in a gas turbine engine. The system may comprise one or more heatable collecting elements configured to be positioned in a fuel supply passage having an inlet and an outlet. The apparatus heatable collecting may be configured to generate heat at or over a fuel system temperature range to induce coking in at least one of the heatable collecting elements. The apparatus may also include a sensor configured to detect an indication of coking on the heatable collecting elements and, in response to the coking indication, communicate a coking condition signal to an engine control.
    Type: Application
    Filed: December 26, 2018
    Publication date: May 9, 2019
    Inventors: David Farnum, Douglas D. Dierksmeier, Ben Moloney, Patrick C. Sweeney
  • Patent number: 10248884
    Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.
    Type: Grant
    Filed: April 10, 2017
    Date of Patent: April 2, 2019
    Assignee: Linear Algebra Technologies Limited
    Inventors: David Moloney, Alireza Dehghani
  • Publication number: 20180349147
    Abstract: The present application relates generally to a parallel processing device. The parallel processing device can include a plurality of processing elements, a memory subsystem, and an interconnect system. The memory subsystem can include a plurality of memory slices, at least one of which is associated with one of the plurality of processing elements and comprises a plurality of random access memory (RAM) tiles, each tile having individual read and write ports. The interconnect system is configured to couple the plurality of processing elements and the memory subsystem. The interconnect system includes a local interconnect and a global interconnect.
    Type: Application
    Filed: February 20, 2018
    Publication date: December 6, 2018
    Inventors: David Moloney, Richard Richmond, David Donohoe, Brendan Barry
  • Publication number: 20180246725
    Abstract: The present application discloses a computing device that can provide a low-power, highly capable computing platform for computational imaging. The computing device can include one or more processing units, for example one or more vector processors and one or more hardware accelerators, an intelligent memory fabric, a peripheral device, and a power management module. The computing device can communicate with external devices, such as one or more image sensors, an accelerometer, a gyroscope, or any other suitable sensor devices.
    Type: Application
    Filed: February 20, 2018
    Publication date: August 30, 2018
    Inventors: Brendan Barry, Richard Richmond, Fergal Connor, David Moloney
  • Patent number: 10019195
    Abstract: For each storage array in a storage system, a single value score indicative of the overall health of the respective storage array is calculated. Storage array health score may be tracked over time and used to identify storage arrays in need of maintenance. The storage array health score may be calculated as a composite of four component scores: physical component health, logical component health, Service Level Objective compliance and Best Practice Configuration Compliance. The physical component and logical component scores may be based on multiple different category health scores, and each category health score may be based on multiple instance health scores. Health scores may be used to identify remedial actions and predict health score increase as a result of remedial actions.
    Type: Grant
    Filed: June 27, 2016
    Date of Patent: July 10, 2018
    Assignee: EMC IP HOLDINGS COMPANY LLC
    Inventors: Fatemeh Azmandian, Ron Arnan, Amnon Naamad, David Moloney
  • Publication number: 20180189066
    Abstract: The present application provides a method of randomly accessing a compressed structure in memory without the need for retrieving and decompressing the entire compressed structure.
    Type: Application
    Filed: December 27, 2017
    Publication date: July 5, 2018
    Inventor: David Moloney
  • Patent number: 10001993
    Abstract: A vector processor is disclosed including a variety of variable-length instructions. Computer-implemented methods are disclosed for efficiently carrying out a variety of operations in a time-conscious, memory-efficient, and power-efficient manner. Methods for more efficiently managing a buffer by controlling the threshold based on the length of delay line instructions are disclosed. Methods for disposing multi-type and multi-size operations in hardware are disclosed. Methods for condensing look-up tables are disclosed. Methods for in-line alteration of variables are disclosed.
    Type: Grant
    Filed: August 12, 2014
    Date of Patent: June 19, 2018
    Assignee: Linear Algebra Technologies Limited
    Inventors: Brendan Barry, Fergal Connor, Martin O'Riordan, David Moloney, Sean Power