http://iet.metastore.ingenta.com
1887

Observation of positive Lyapunov exponent induced by gain increase of neuron nonlinearity in complex-valued associative memories

Observation of positive Lyapunov exponent induced by gain increase of neuron nonlinearity in complex-valued associative memories

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

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

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:
 
 
 
 
 
Electronics Letters — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

A positive Lyapunov exponent is observed in complex-valued associative memories having dynamical attractors, when a small-signal gain of neuron nonlinearity is increased. When the gain is small, the Lyapunov exponent is constantly zero (normal behaviour). However, it is found in the experiment that, unlike conventional (real-valued) associative memories, the Lyapunov exponent becomes distinctly positive (chaotic behaviour) for a larger neuron gain even if the weighting factors are unchanged. This result suggests that the gain of nonlinear devices has a critical significance on information processing stability in future coherent neural networks.

References

    1. 1)
      • B. Widrow , J. McCool , M. Ball . The complex LMS algorithm. Proc. IEEE , 719 - 720
    2. 2)
      • G.M. Georgiou , C. Koutsougeras . Complex domain backpropagation. IEEE Trans. Circuits Syst. II, Analog Digit. Signal. Process. , 330 - 334
    3. 3)
      • A. Hirose . Continuous complex-valued backpropagation learning. Electron. Lett. , 1854 - 1855
    4. 4)
      • Hirose, A., Eckmiller, R.: `Coherent optical neural networks: Generalization ability in frequencydomain', ICNN'95 Perth 1995 Proc. 6, p. 3204–3209.
    5. 5)
      • A. Hirose . Applications of complex-valued neural networks to coherent optical computingusing phase sensitive detection scheme. Inf. Sci. - Applications , 103 - 117
    6. 6)
      • Aihara, K.: `Spatio-temporal dynamics and possible computation in chaotic neural networks', WCNN'95 Washington D.C. 1995 Proc. I, p. 262-265.
    7. 7)
      • Stiber, M., Segundo, J.P.: `Learning in neural models with complex dynamics', IJCNN'93 Nagoya 1993 Proc. I, p. 405–408.
    8. 8)
      • Hodge, A., Newcomb, R.W.: `VLSI chaos generation - Hysteresis and the neural type cell', WCNN'95 Washington D.C. 1995 Proc. I, p. 250–253.
    9. 9)
      • Kanou, N., Horio, Y.: `Design of current-mode transiently chaotic neural networks for travelingsalesman problem', WCNN'95 Washington D.C. 1995 Proc. I, p. 282–285.
http://iet.metastore.ingenta.com/content/journals/10.1049/el_19960472
Loading

Related content

content/journals/10.1049/el_19960472
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address