论文信息 - Hopfield model with complementary binary representations

Hopfield model with complementary binary representations

A Hopfield neural network model with complementary binary representations is proposed. Advantages of this approach are improvement in memory capacity and error-correction capability when compared with conventional binary models. Some requirements of the Hopfield model necessary to obtain perfect recall can also be relaxed.

Heng-Ming Tai | T.-L. Jong

[1] 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.

[2] D Psaltis,et al. Optical information processing based on an associative-memory model of neural nets with thresholding and feedback. , 1985, Optics letters.

[3] J J Hopfield,et al. Collective computation in neuronlike circuits. , 1987, Scientific American.

[4] H H Arsenault,et al. Optical associative memory model based on neural networks having variable interconnection weights. , 1987, Applied optics.

[5] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[6] R A Athale,et al. Optical implementation of associative memory with controlled nonlinearity in the correlation domain. , 1986, Optics letters.