Abstract
This paper presents an implementation methodology of weighted ANNs whose weights have already been computed. The validation of this technique is made through the synthesis of circuits implementing the behaviour of specialised ANNs compiled from sets of logical clauses describing different logical problems. ANeuro–Symbolic Language (NSL) and its compiler5 have been designed and implemented in order to translate the neural representation of a given logical problem into the corresponding VHDL code, which in turn can set devices such as FPGA(Field Programmable Gate Array). The result of this operation leads to an electronic circuit called NSP (Neuro–Symbolic Processor) that effectively implements a massively parallel interpreter of logic programs.
Copyright n. 001109/D801353—23/12/98.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
V. Beiu, “New VLSI complexity results for threshold gate comparison,” Proc. of SBRN’96 (1996).
V. M. G. Ferreira and F. M. G. Franca, “Weightless implementations of weighted neural networks,” Proc. of the IV Brazilian Symposium on Neural Networks—SBRN’97, Goiania, GO, Brazil, vol. II, 53–54 (1997).
W. S. McCulloch and W. Pitts, “ALogical Calculus of the Ideas Immanent in the Nervous Activity,” Bull. Math. Bioph. 1943.
A. Aiello, E. Burattini, G. Tamburrini, “Purely Neural, Rule-Based Diagnostic Systems. Part I: Production Rules,” International Journal of Intelligent Systems, 10, 735–749 (1995).
J. von Neumann, “Probabilistic Logics and the Synthesis of Reliable Organisms from Unreliable Components,” Automata Studies, Princeton (1956).
M. L. Minsky, “Computation: Finite and Infinite Machines,” Prentice Hall (1967).
M. Hilario, “An Overview of Strategies for Neuro-Symbolic Integration,” in Sun R. and Alexandre F. (eds.), 1–6 (1995).
E. Burattini and G. Tamburrini, “APseudo-Neural System for Hypothesis Selection,” International Journal of Intelligent Systems, 193–209 (1992).
A. Aiello, E. Burattini, G. Tamburrini, “Neural Networks and Rule-Based Systems,” Fuzzy Logic and Expert Systems Applications, Accademic Press (1998).
E. Burattini, M. De Gregorio, G. Tamburrini, “Neuro-Symbolic Processing: Non-Monotonic Operators and their FPGA Implementation,” Proc. Sixth Brazilian Symposium on Neural Networks—SBRN 2000, IEEE Press, 2–6 (2000).
E. Burattini, A. de Francesco and M. De Gregorio, “NSL: A Neuro-Symbolic Language for Monotonic and Non-Monotonic Logical Inferences,” Proc. Seventh Brazilian Symposium on Neural Networks—SBRN 2002, IEEE Press, in press (2002).
C. K. Ng and T. G. Clarkson, “The VLSI design of a neural network processing element: the pRAM module,” Weightless Neural Network Workshop’ 93, Computing with Logical Neurons, 134–138, (1993).
J. J. Vidal, “Implementing neural nets with Programmable Logic,” IEEE Trans. on Acoustics, Speech, and Signal Processing, 36, 7, July (1988).
E. Burattini, M. De Gregorio, G. Improta, “Anew traffic light single junction control system implemented by a neural network,” in Networks in Transport Applications, Eds. V. Himanen, P. Nijkamp, A. Reggiani, Ashgate Pub. Ltd, Aldeeshot, England, 193–209 (1998).
M. L. Minsky, “Some universal elements for finite automata,” Automata Studies, Princeton (1956).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Burattini, E., De Gregorio, M., Ferreira, V.M.G., França, F.M.G. (2003). NSP: a Neuro–Symbolic Processor. In: Mira, J., Álvarez, J.R. (eds) Artificial Neural Nets Problem Solving Methods. IWANN 2003. Lecture Notes in Computer Science, vol 2687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44869-1_2
Download citation
DOI: https://doi.org/10.1007/3-540-44869-1_2
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40211-4
Online ISBN: 978-3-540-44869-3
eBook Packages: Springer Book Archive