Zobrazeno 1 - 10
of 56
pro vyhledávání: '"G.G. Coghill"'
Autor:
W.K. Lai, G.G. Coghill
Publikováno v:
IEEE Transactions on Vehicular Technology. 45:91-96
The problem of assigning appropriate channels to the individual members of a cellular network is an important challenge facing network designers. Heuristics may be used to solve this problem, although in recent years parallel distributed methods have
Autor:
G.G. Coghill, C. Laufer
Publikováno v:
IJCNN
The Cerebellar Model Articulation Controller (CMAC) neural network is an associative memory that is biologically inspired by the cerebellum, which is found in the brains of animals. In recent works, the kernel recursive least squares CMAC (KRLS-CMAC)
Autor:
Charles P. Unsworth, G.G. Coghill, Ken Gledhill, M. Chadwick, Sepideh Jafarzadeh Rastin, R. Robinson
Publikováno v:
ISSPA
This paper includes the main topics associated with seismic noise modeling. First part will describe the seismic noise modeling bases and its corresponding mathematical approaches. The second part will review the main approaches taken in practice to
Autor:
Sepideh Jafarzadeh Rastin, Charles P. Unsworth, G.G. Coghill, Ken Gledhill, M. Chadwick, R. Robinson
Publikováno v:
ISSPA
This paper introduces a new method to determine simplified earthquake event waveforms (SEEW) of regional earthquakes from their seismological signals which are heavily plagued with seismic noise. This method iteratively couples a standardised earthqu
Autor:
S. J. Kia, G.G. Coghill
Publikováno v:
Biological Cybernetics. 67:433-443
In this paper, an unsupervised learning algorithm is developed. Two versions of an artificial neural network, termed a differentiator, are described. It is shown that our algorithm is a dynamic variation of the competitive learning found in most unsu
Publikováno v:
2008 IEEE International Conference on Industrial Technology.
A method for the parallel implementation of artificial neural networks (ANN), using digital logic, is presented. Uniformly weighted bit-streams are used to represent bipolar analogue signals. Operations necessary for neural network behaviour like sum
Publikováno v:
IEEE transactions on neural networks. 18(5)
A new method for the parallel hardware implementation of artificial neural networks (ANNs) using digital techniques is presented. Signals are represented using uniformly weighted single-bit streams. Techniques for generating bit streams from analog o
Publikováno v:
ACC
A new method for the parallel hardware implementation of artificial neural network (ANN) using digital techniques is presented. Uniformly weighted bit-streams are used to represent bipolar analogue signals. Operations necessary for neural network beh
Publikováno v:
2006 IEEE International Conference on Industrial Technology.
A new technique for the hardware implementation of real time fuzzy controllers is presented. This technique uses uniformly weighted bit-streams to represent analogue signals. The technique lends itself to implementation on Field Programmable Gate Arr
Publikováno v:
TENCON 2005 - 2005 IEEE Region 10 Conference.
The present study proposes an alternate strategy for implementing controllers based on bit-streams. The key to the success of bit-stream controllers is their ability to represent continuous time signals using uniformly weighted binary streams. These