Patents by Inventor James Denham

James Denham 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: 20210380223
    Abstract: The aircraft control system 100 includes an inceptor with a set of primary inceptor axes and a set of secondary inceptor inputs. The inceptor can optionally include a hand rest, a thumb groove, a set of finger grooves, passive soft stops, and/or any other additional elements. The aircraft control system can optionally include a flight controller, aircraft sensors, effectors, and a haptic feedback mechanism. However, the aircraft control system 100 can additionally or alternatively include any other suitable components.
    Type: Application
    Filed: June 7, 2021
    Publication date: December 9, 2021
    Inventors: Blake English, James Denham, Justin Paines
  • Patent number: 10510001
    Abstract: This invention solves the long-standing problem in Machine Learning of training a neural network on a spike-based neuromorphic computer. The preferred embodiment of the invention describes an algorithm for training a Restricted Boltzmann Machine (RBM) neural network, but the invention applies equally to training neural networks in the general class of Markov Random Fields. The standard CD algorithm for training an RBM on a general-purpose computer is unsuitable for implementation on a neuromorphic computer, as it requires the communication of real-valued parameter values between neurons, and/or shared memory access by neurons to stored parameter values. By employing the invention described, these requirements are eliminated, thus providing a training algorithm which can be implemented efficiently on a spike-based, distributed processor and memory, neuromorphic computer system.
    Type: Grant
    Filed: March 17, 2017
    Date of Patent: December 17, 2019
    Assignee: Mindtrace Limited
    Inventor: Michael James Denham
  • Publication number: 20170270410
    Abstract: This invention solves the long-standing problem in Machine Learning of training a neural network on a spike-based neuromorphic computer. The preferred embodiment of the invention describes an algorithm for training a Restricted Boltzmann Machine (RBM) neural network, but the invention applies equally to training neural networks in the general class of Markov Random Fields. The standard CD algorithm for training an RBM on a general-purpose computer is unsuitable for implementation on a neuromorphic computer, as it requires the communication of real-valued parameter values between neurons, and/or shared memory access by neurons to stored parameter values. By employing the invention described, these requirements are eliminated, thus providing a training algorithm which can be implemented efficiently on a spike-based, distributed processor and memory, neuromorphic computer system.
    Type: Application
    Filed: March 17, 2017
    Publication date: September 21, 2017
    Inventor: Michael James Denham