K
K.M. Curtis
Researcher at University of Nottingham
Publications - 11
Citations - 232
K.M. Curtis is an academic researcher from University of Nottingham. The author has contributed to research in topics: Artificial neural network & 3D single-object recognition. The author has an hindex of 6, co-authored 11 publications receiving 210 citations.
Papers
More filters
Journal ArticleDOI
Piecewise linear approximation applied to nonlinear function of a neural network
TL;DR: An efficient piecewise linear approximation of a nonlinear function (PLAN) is proposed that uses a simple digital gate design to perform a direct transformation from X to Y, where X is the input and Y is the approximated sigmoidal output.
Journal ArticleDOI
Consideration of multiplexing in neural network hardware
TL;DR: Research into a scheme for overcoming the communications 'bottleneck' within hardware neural networks, utilising frequency division multiplexing of amplitude modulated neural signals, using the FDM solution is presented.
Journal ArticleDOI
Frequency division multiplexing in analogue neural network
TL;DR: Simulation results on network learning and generalisation show that the neural network is tolerant to as much as 50% overlap of frequency responses of filters used in demultiplexing.
A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
TL;DR: A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime.
Proceedings ArticleDOI
Shape recognition using a novel fractal technique
TL;DR: A new rotational invariance algorithm is presented which makes the recognition process inherently rotationally invariant, and applied to a difficult recognition problem.