Fault tolerance of neural associative memories

Access Full Text

Fault tolerance of neural associative memories

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IEE Proceedings E (Computers and Digital Techniques) — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Electrical Engineers
Published

The effects of hardware limitations and fabrication faults on the fault tolerance of neural associative memories using the Hopfield interconnect topology are investigated. It is shown that neural computing structures are not by definition fault tolerant, and that the degree of tolerance is very sensitive to the assumed physical fault model and to the nature of the stored information.

Inspec keywords: content-addressable storage; fault tolerant computing; neural nets

Other keywords: fault tolerance; hardware limitations; Hopfield interconnect topology; fabrication faults; neural associative memories

Subjects: Artificial intelligence (theory); Performance evaluation and testing; Other digital storage

References

    1. 1)
      • R. Hecht-Nielsen . Neurocomputing picking the human brain. IEEE Spectr. , 3 , 36 - 41
    2. 2)
      • Brause, R.: `Pattern recognition and fault tolerance in non-linear neural networks', Proc. 1st INNS meeting, 1988, Pergamon Press, , p. 13.
    3. 3)
      • M. Cottrell . Stability and attractivity in associative memory networks. Biol. Cybern. , 2 , 129 - 139
    4. 4)
      • Nijhuis, J.A.G.: ‘NNSIM A neural network simulator vs 2.0’.
    5. 5)
      • R.J. McEliece , E.C. Posner , E.R. Rodemich , S.S. Venkatesh . The capacity of the Hopfield associative memory. IEEE Trans. Inform. Theory , 4 , 461 - 482
    6. 6)
      • J. Jou , J.A. Abraham . Fault-tolerant matrix arithmetic and signal processing on highly concurrent computing structures. Proc. IEEE , 5 , 732 - 741
    7. 7)
      • D.B. Swartz , R.E. Howard , J.S. Denker , R.W. Epworth , H.P. Graf , W. Hubbard , L.D. Jackel , B. Straughn , D.M. Tennant . Dynamics of microfabricated electronic neural networks. Appl. Phys. Lett. , 16 , 1110 - 1112
    8. 8)
      • W.R. Moore , R. Eckmiller , C. V.D. Malsburg . (1988) Conventional fault-tolerance and neural computers, Neural Computers.
    9. 9)
      • R.E. Howard , L.D. Jackel , H.P. Graf . Electronic neural networks. AT&T Tech. J. , 1 , 58 - 64
    10. 10)
      • J.J. Hopfield . Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA , 2554 - 2558
    11. 11)
      • B. Hoefflinger , G. Conte , D. Esteve , P. Weisglas . (1988) , PRO-CHIP.
    12. 12)
      • J.S. Denker . Neural networks models of learning and adaptation. Physica 22D , 216 - 232
    13. 13)
      • R.G. Bennetts . (1984) , Design of testable logic circuits.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-e.1989.0052
Loading

Related content

content/journals/10.1049/ip-e.1989.0052
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading