Abstract
LANN27 is an electronic device implementing in discrete electronics a 27 neurons, fully connected attractor neural network with stochastic learning. We summarize in this paper some key features emerged by extensive tests performed to elucidate the neuronal collective dynamics, the learning dynamics and the memory capacity of the LANN27 device.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
D.J. Amit, “Modeling brain function”, Cambridge University Press, 1989
D. Badoni, S. Bertazzoui, S. Buglioni, G. Salina, D.J. Amit and S. Fusi “Electronic implementation of an analogue neural network with stochastic transitions”, Network, 6 125 (1995)
D.J. Amit and S. Risi “Learning in neural networks with material synapses”, Neural Computation 6 957 (1994)
N Brunei, F Carusi and S Fusi “Slow stochastic Hebbian learning of classes of stimuli”, submitted to Network
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Del Giudice, P., Fusi, S. (1997). Attractor dynamics in an electronic neural network. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020325
Download citation
DOI: https://doi.org/10.1007/BFb0020325
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive