The auto-associative Hopfield network is a set of neurons in which the output of each neuron is the input of all other neurons, i.e. the inter-neuronal connections graph of the Hopfield network is complete. The large number of inter-neuronal connections is one of the problems of the Hopfield networks hardware implementation. A solution is the reduction (exclusion) of insignificant connections. In this paper, based on the analogy with oscillator networks, the connections number reducing effect on the auto-associative Hopfield network behavior is investigated. It is shown that the exclusion of connections with weights whose absolute values are strictly less than the maximum for a given neuron substantially improves the operation quality of the Hopfield network trained according to the Hebb's rule. As the dimension of the stored vectors increases, not only the chimeras disappear but the permissible input data noise level also increases. At the same time, the network connections number is reduced by 13-17 times. The reduction of connections in the Hopfield network, trained by the projection method, worsens its functioning quality, namely: in the network output data, there are distortions even while the reference vectors are entered. With the stored vectors dimension increasing, the allowable noise level for the reduced Hopfield - Hebb networks approaches the corresponding index for the Hopfield projection networks. Thus, given the much smaller number of connections in the reduced Hopfield - Hebb networks, these networks can successfully compete with the Hopfield projection networks for a sufficiently large stored vectors dimension.
Download file
Counter downloads: 181
- Title Reduction of synapses in the Hopfield autoassociative memory
- Headline Reduction of synapses in the Hopfield autoassociative memory
- Publesher
Tomsk State University
- Issue Prikladnaya Diskretnaya Matematika - Applied Discrete Mathematics 37
- Date:
- DOI 10.17223/20710410/37/9
Keywords
автоассоциативная память Хопфилда, правило Хебба, проекционный метод, осцилляторная сеть, редукция связей, auto-associative Hopfield memory, Hebb's rule, projection method, oscillatory network, reduction of connectionsAuthors
References
Осовский С. Нейронные сети для обработки информации. М.: Финансы и статистика, 2002. 344с.
Hopfield J. Neural networks and physical systems with emergent collective computational abilities // Proc. National Academy of Science USA. 1982. V. 79. P. 2554-2558.
Personnaz L., Guyon I., and Dreyfus G. Collective computational properties of neural networks: New learning mechanisms // Phys. Rev. A. 1986. V. 34. No. 5. P. 4217-4228.
Michel A.N. and Liu D. Qualitative Analysis and Synthesis of Recurrent Neural Networks. N.Y.: Marcel Dekker Inc., 2002. 504 p.
Hu S. G., Liu Y., Liu Z., et al. Associative memory realized by a reconfigurable memristive Hopfield neural network // Nature Commun. 2015. V. 6. Article no. 7522.
Тарков М. С. Сеть Хопфилда с межнейронными соединениями на основе мемристорных мостов // Труды XVIII Междунар. науч.-технич. конф. «НЕЙРОИНФОРМАТИКА-2016». М.: МИФИ, 2016. Ч.3. С. 91-100.
Tarkov M. S. Hopfield network with interneuronal connections based on memristor bridges // LNCS. 2016. V. 9719. P. 196-203.
Tarkov M. S. Oscillatory neural associative memories with synapses based on memristor bridges // Optical Memory and Neural Networks (Information Optics). 2016. V. 25. No. 4. P. 219-227.
Горбань А. Н., Россиев Д. А. Нейронные сети на персональном компьютере. Новосибирск: Наука, 1996. 276 c.
Maffezzoni P., Bahr B., Zhang Z., and Daniel L. Analysis and design of Boolean associative memories made of resonant oscillator arrays // IEEE Trans. Circuits Systems I: Regular Papers. 2016. V. 63. No. 8. P. 1964-1973.

Reduction of synapses in the Hopfield autoassociative memory | Prikladnaya Diskretnaya Matematika - Applied Discrete Mathematics. 2017. № 37. DOI: 10.17223/20710410/37/9
Download full-text version
Counter downloads: 615