Multivalley structure of attractor neural networks

By C. R. Neto, José Fernando Fontanari. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. J. Urgen Schmidhuber
2. Sjoerd van Steenkiste
3. Klaus Greff
4. Yoshua Bengio
5. Sergey Levine
6. Quoc V. Le
7. Mohit Bansal
8. Trevor Darrell

Citations in the corpus

• On the Binding Problem in Artificial Neural Networks (2020, background): “In particular, the fact that each weight participates in the specification of many attractors can lead to spurious (unintended) attractors and illconditioned attraction basins (Neto and Fontanari, 1999).”
• Localist Attractor Networks (2001, background): “Training procedures are CPU intensive and often produce spurious attractors and ill-conditioned attractor basins (e.g., Mathis, 1997; Rodrigues & Fontanari, 1997).”