论文信息 - Pattern-specific neural network design

Pattern-specific neural network design

We present evidence that the performance of the traditional fully connected Hopfield model can be dramatically improved by carefully selecting an information-specific connectivity structure, while the synaptic weights of the selected connections are the same as in the Hopfield model. Starting from a completely disconnected network we let “genuine” Hebbian synaptic connections grow, one by one, until a desired degree of stability is achieved. Neural pathways are thus fixed notbefore, butduring the learning phase.

Karl E. Kürten | Martin Anderle | Herwig K. Schweng | Karl W. Kratky

[1] P. Kuhlmann,et al. A dilution algorithm for neural networks , 1992 .

[2] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[3] Karl E. Kürten,et al. Quasi-optimized memorization and retrieval dynamics in sparsely connected neural network models , 1990 .

[4] Karl E. Kürten. Adaptive architectures for Hebbian network models , 1992 .

[5] Janowsky,et al. Pruning versus clipping in neural networks. , 1989, Physical review. A, General physics.