Výsledky vyhledávání - "Howard, Gerard David"

Report

A Staged Approach to Evolving Real-world UAV Controllers

Autor: Howard, Gerard David, Elfes, Alberto

A testbed has recently been introduced that evolves controllers for arbitrary hover-capable UAVs, with evaluations occurring directly on the robot. To prepare the testbed for real-world deployment, we investigate the effects of state-space limitation

Externí odkaz: http://arxiv.org/abs/1905.10762

Zobrazit plný text záznamu

Report

On Self-Adaptive Mutation Restarts for Evolutionary Robotics with Real Rotorcraft

Autor: Howard, Gerard David

Self-adaptive parameters are increasingly used in the field of Evolutionary Robotics, as they allow key evolutionary rates to vary autonomously in a context-sensitive manner throughout the optimisation process. A significant limitation to self-adapti

Externí odkaz: http://arxiv.org/abs/1703.10754

Zobrazit plný text záznamu

Dissertation/ Thesis

Constructivist and spiking neural learning classifier systems

Autor: Howard, Gerard David

This thesis investigates the use of self-adaptation and neural constructivism within a neural Learning Classifier System framework. The system uses a classifier structure whereby each classifier condition is represented by an artificial neural networ

Externí odkaz: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.573442

Zobrazit plný text záznamu

Report

Evolving Spiking Networks with Variable Resistive Memories

Autor: Howard, Gerard David, Bull, Larry, Costello, Ben de Lacy, Adamatzky, Andrew, Gale, Ella

Publikováno v: Evolutionary Computation, Spring 2014, Vol. 22, No. 1, Pages 79-103 Posted Online February 7, 2014

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural n

Externí odkaz: http://arxiv.org/abs/1505.04357

Zobrazit plný text záznamu

Report

Organic Memristor Devices for Logic Elements with Memory

Autor: Erokhin, Victor, Howard, Gerard David, Adamatzky, Andrew

Publikováno v: Int J Bifurcation Chaos 22 (2012) 1250283

Memristors are promising next-generation memory candidates that are nonvolatile, possess low power requirements and are capable of nanoscale fabrication. In this article we physically realise and describe the use of organic memristors in designing st

Externí odkaz: http://arxiv.org/abs/1212.3425

Zobrazit plný text záznamu