NDRAM: nonlinear dynamic recurrent associative memory for learning bipolar and nonbipolar correlated patterns

@article{Chartier2005NDRAMND,
  title={NDRAM: nonlinear dynamic recurrent associative memory for learning bipolar and nonbipolar correlated patterns},
  author={Sylvain Chartier and Robert Proulx},
  journal={IEEE Transactions on Neural Networks},
  year={2005},
  volume={16},
  pages={1393-1400}
}
This paper presents a new unsupervised attractor neural network, which, contrary to optimal linear associative memory models, is able to develop nonbipolar attractors as well as bipolar attractors. Moreover, the model is able to develop less spurious attractors and has a better recall performance under random noise than any other Hopfield type neural network. Those performances are obtained by a simple Hebbian/anti-Hebbian online learning rule that directly incorporates feedback from a specific… CONTINUE READING
34 Citations
16 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 34 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 16 references

A new online unsupervised learning rule for the BSB model

  • S. Chartier, R. Proulx
  • Proc. Int. Joint Conf. Neural Networks (IJCNN’01…
  • 2001
1 Excerpt

Discrete optimization using analog neural networks with discontinuous dynamics

  • M. Vidyasagar
  • Int. Conf. Automation, Robotics, Computer Vision…
  • 1994
1 Excerpt

Learning grey-toned patterns in neural networks

  • S. Mertens, H. M. Koehler, S. Bos
  • J. Phys. A: Math. Gen., vol. 25, pp. 5039–5045…
  • 1992
1 Excerpt

Similar Papers

Loading similar papers…