Abstract
In this paper, we examine Hopfield network composed of multi-state neurons for storing sequence data as limit cycles of the network. Earlier, we had presented uni-modal data - particularly text, speech and audio data storage and retrieval in bipolar Hopfield based associative memory architecture. We extended this to multi-modal data and we demonstrated that Hopfield can indeed work as content addressable memory for multi-modal data. This paper is a step towards realising a more wider definition of multi-modality. We present a M-ary Hopfield associative memory model for storing limit cycle data. The proposed system uses a dual weight learning mechanism to exhibit limit cycle behavior in which sequence data can be stored and retrieved. We particularly deal with a) sequence of images and b) movie clip data as instances of limit cycle data. We also propose and use a two stage firing mechanism to retrieve the stored sequence data from the limit cycles. We present a trade-off behavior between the number of cycles and length of cycles the network can store and we demonstrate that the network capacity is still of the order of network size i.e., O(N) for limit cycle data. This represents a first of its kind attempt for sequence storage and retrieval in Hopfield network as limit-cycles, particularly with image-sequence and movie-content data of real-world scales.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Roenneberg, T., Chua, E.J., Bernardo, R., Mendoza, E.: Modelling biological rhythms. Curr. Biol. 18(17), R826–R835 (2008)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. 79(8), 2554–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. 81(10), 3088–3092 (1984)
Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice Hall PTR, USA (1998)
Ladwani, V.M., Vaishnavi, Y., Ramasubramanian, V.: Hopfield auto-associative memory network for content-based text-retrieval. In: Proceedings of 26th International Conference on Artificial Neural Networks, ICANN-2017, Alghero, Italy (September 2017)
Ladwani, V.M., et al.: Hopfield net framework for audio search. In: Proceedings of the 23rd National Conference on Communications (NCC), NCC-2017, pp. 1–6 (2017)
Vaishnavi, Y., Shreyas, R., Suhas, S., Surya, U.N., Ladwani, V.M., Ramasubramanian, V.: Associative memory framework for speech recognition: adaptation of hopfield network. In: Proceedings of the IEEE Annual India Conference, INDICON-2016, pp. 1–6 (2016)
Shriwas, R., Joshi, P., Ladwani, V.M., Ramasubramanian, V.: Multi-modal Associative Storage and Retrieval Using Hopfield Auto-associative Memory Network. In: Tetko, I.V., Kurková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 57–75. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30487-4_5
Hebb, D. O. the organization of behavior: a neuropsychological theory. New York: John Wiley and Sons, Inc., 1949. 335 p. Sci. Educ. 34(5), 336–337 (1950)
Wang, D.: The Handbook of Brain Theory and Neural Networks, 2nd edn. Choice Reviews Online, pp. 1163–1167 (2003)
Denizdurduran, B.: Attractor Neural Network Approaches in the Memory Modeling (2012)
Miyoshi, S., Nakayama, K.: A recurrent neural network with serial delay elements for memorizing limit cycles. In: Proceedings of the International Conference on Neural Networks, ICNN 1995. IEEE (1995)
Miyoshi, S., Yanai, H.-F., Okada, M.: Associative memory by recurrent neural networks with delay elements. Neural Netw. 17(1), 55–63 (2004)
Maurer, A., Hersch, M., Billard, A.G.: Extended hopfield network for sequence learning: application to gesture recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 493–498. Springer, Heidelberg (2005). https://doi.org/10.1007/11550822_77
Zhang, C., Dangelmayr, G., Oprea, I.: Storing cycles in hopfield-type networks with pseudoinverse learning rule: admissibility and network topology. Neural Netw. 46, 283–298 (2013)
Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. IJCV 123(1), 74–93 (2017)
Bijjani, R., Das, P.: An M-ary neural network model. Neural Comput. 2(4), 536–551 (1990)
Rolls, E.T., Treves, A., Foster, D., Perez-Vicente, C.: Simulation studies of the CA3 hippocampal subfield modelled as an attractor neural network. Neural Netw. 10(9), 1559–1569 (1997)
Personnaz, L., Guyon, I., Dreyfus, G.: Collective computational properties of neural networks: new learning mechanisms. Phys. Rev. A 34(5), 4217 (1986)
Zlatintsi, A., et al.: COGNIMUSE: a multimodal video database annotated with saliency, events, semantics and emotion with application to summarization. EURASIP J. Image Video Process. 2017(1), 1–24 (2017). https://doi.org/10.1186/s13640-017-0194-1
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ladwani, V.M., Ramasubramanian, V. (2021). M-ary Hopfield Neural Network Based Associative Memory Formulation: Limit-Cycle Based Sequence Storage and Retrieval. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12894. Springer, Cham. https://doi.org/10.1007/978-3-030-86380-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-030-86380-7_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86379-1
Online ISBN: 978-3-030-86380-7
eBook Packages: Computer ScienceComputer Science (R0)