Abstract
The pRAM is a non-linear stochastic device with neuron-like behaviour. The pRAM generates an output in the form of a spike train. The spike train may be integrated over a variable number of time steps to control the amount of noise in the system. The pRAM is realisable in hardware and VLSI devices have been built. Learning algorithms have been developed for the pRAM which may be incorporated in hardware and the intrinsic noise in the pRAM has proved beneficial during training. A current application of a pRAM net is in real-time object recognition.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
W S McCulloch and W Pitts, “A logical calculus of the ideas immanent in nervous activity”, Bulletin of Mathematical Biophysics, 5, 115–133, 1943.
I Aleksander, “Microcircuit learning computers”, Mills and Boon, London, 1971.
T G Clarkson, D Gorse and J G Taylor, “Hardware realisable models of neural processing”, Proc. 1st IEE Int. Conf. on Artificial Neural Networks, London, 242–246, 1989.
T G Clarkson, D Gorse and J G Taylor, “From wetware to hardware: reverse engineering using probabilistic RAMs”, Journal of Intelligent Systems, Freund, London, in press.
T G Clarkson, D Gorse and J G Taylor, “Biologically plausible learning in hardware realisable nets”, Proc. ICANN91 Conf., Helsinki, 195–199, 1991.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag London Limited
About this paper
Cite this paper
Clarkson, T.G. (1992). The pRAM as a hardware-realisable neuron. In: Taylor, J.G. (eds) Neural Network Applications. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-2003-2_11
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2003-2_11
Publisher Name: Springer, London
Print ISBN: 978-3-540-19772-0
Online ISBN: 978-1-4471-2003-2
eBook Packages: Springer Book Archive