A robust method for distinguishing between learned and spurious attractors

Neural Networks

Volumn 17, Issue 3, 2004, Pages 313-326

  Robins, Anthony V ^a   McCallum, Simon J R ^a  

^a UNIVERSITY OF OTAGO   (New Zealand)

Author keywords

Energy profile; Familiarity; Hopfield net; Recognition; Spurious pattern; Spurious state

Indexed keywords

LEARNING SYSTEMS; RANDOM PROCESSES; ROBUSTNESS (CONTROL SYSTEMS);

LEARNED ATTRACTORS;

NEURAL NETWORKS;

ARTICLE; ASSOCIATION; ENERGY; LEARNING; NERVE CELL NETWORK; PRIORITY JOURNAL; RECALL; RECOGNITION; SATISFACTION;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; ASSOCIATION LEARNING; COMPUTER SIMULATION; HUMANS; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS;

EID: 1642349422     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2003.11.007     Document Type: Article

References (19)

1. Amari S., Maginu K. Statistical neurodynamics of associative memory. Neural Networks. 1:1988;63-73.
2. Bogacz R., Brown M.W., Giraud-Carrier C. Model of familiarity discrimination in the perirhinal cortex. Journal of Computational Neuroscience. 10:2001;5-23.
3. Christos G. Investigation of the Crick-Mitchison reverse-learning dream sleep hypothesis in a dynamical setting. Neural Networks. 9:1996;427-434.
4. Crick F., Mitchison G. The function of dream sleep. Nature. 304:1983;111-114.
5. Davey N., Adams R. Stochastic dynamics and high capacity associative memories. Proceedings of the Ninth International Conference on Neural Information Processing. Vol. 4:2002;1666-1671.
6. Drogosz M., Nowak A., Lewenstein M., Tarkowski W., Zochowski M. Applications of dynamical networks to the explanation of affective-cognitive interactions. Proceedings of the Second Conference on Neural Networks and their Applications, Szczyrk, Poland. 1996;. pp. 110-117.
7. Gardner E. Maximum storage capacity in neural networks. Europhysics Letters. 4:1987;257-270.
8. Gardner E., Stroud N., Wallace D. Training with noise and the storage of correlated patterns in a neural network model. Journal of Physics A: Mathematics and General. 22:1989;2019-2030.
9. Gopalasamy A., Dasgupta C. On the problem of spurious patterns in neural associative memory models. IEEE Transactions on Neural Networks. 6:1997;1483-1491.
10. van Hemmen J. Hebbian learning, its correlation catastrophe, and unlearning. Network. 8:1997;V1-V17.
11. Hertz J., Krough A., Palmer R.G. Introduction to the theory of neural computation. 1991;Addison-Wesley, Redwood City, CA.
12. Hopfield J.J., Feinstein D.I., Palmer R. Unlearning has a stabilising effect in collective memories. Nature. 304:1983;158-159.
13. Johannet A., Personnaz L., Dreyfus G., Gascuel J., Weinfeld M. Specification and implementation of a digital Hopfield-type associative memory with on-chip training. IEEE Transactions on Neural Networks. 3:1992;529-539.
14. Lewenstein M., Nowak A. Recognition with self-control in neural networks. Physical Review A. 40:1989;4652-4664.
15. Norman K.A., O'Reilly R.C. Modeling hippocampal and neocortical contributions to recognition memory: A complementary learning systems approach. Psychological Review. 110:2003;611-646.
16. Robins A., McCallum S. Catastrophic forgetting and the pseudorehearsal solution in Hopfield type networks. Connection Science. 10:1998;121-135.
17. Robins A., McCallum S. The consolidation of learning during sleep: Comparing the pseudorehearsal and unlearning accounts. Neural Networks. 12:1999;1191-1206.
18. Robins A., McCallum S. Learned and spurious attractors in Hopfield type networks. Proceedings of the Fifth Biannual Conference on Artificial Neural Networks and Expert Systems. 2001;The University of Otago, Dunedin, New Zealand. pp. 146-150.
19. Yonelinas A.P. The nature of recollection and familiarity: A review of 30 years of research. Journal of Memory and Language. 46:2002;441-517.