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.

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.

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.