# Multi-strategy learning and deep harmony memory improvisation for self-organizing neurons

- 61 Downloads

## Abstract

This study proposes a concept of representation learning by implementing multi-strategy deep learning harmony memory improvisation for selecting the best harmony of self-organizing neurons. Representation learning is a set of methods that allows a machine to be fed with raw data and to automatically discover the representations needed for detection or classification. In our study, the deep multi-strategy learning involves the convolution of the self-organizing neurons with deep harmony memories improvisation in self-organizing and representation of map learning. The convolution of self-organizing neurons and harmony memory optimize the representation neurons’ weights by generating the optimal best matching unit which is represented as fitness function of \(f_1 \left( x \right) \) and \(f_2 \left( x \right) \). While \(f_1 \left[ {g\left( {{f}''_1 \left( x \right) } \right) } \right] \) and \(f_2 \left[ {g\left( {{f}'_2 \left( x \right) } \right) } \right] \) represent the New Harmony fitness function. The best fitness function, \(f_{{ best}} (x)\) is selected based on the \(f_1 \left( x \right) \) and \(f_2 \left( x \right) \) performance which will be later stored in the harmony memory vector. The position vector of a particle is subjected to the Newtonian mechanics constant acceleration during the interval \(\Delta t\). The search space of self-organizing map with Newton-based particle swarm algorithm particles depends on the width area, \(\sigma _\alpha (t)\) of organizing neurons lattice structure. Our proposed methods are experimented on various biomedical datasets. The findings indicate that the proposed methods provide better quantization error for clustering and good classification accuracy with statistical measurement validations.

## Keywords

Representation learning Machine learning Deep learning Meta-heuristic algorithms Harmony search algorithm Classification and clustering problems## Notes

### Acknowledgements

The authors would like to thank Ministry of Higher Education (MOHE) and Universiti Teknologi Malaysia (UTM) for their support in Research and Development, *UTM Big Data Centre* and the *Soft Computing Research Group* (SCRG) for the inspiration in making this study a success. This work is partially supported by the UTM Research University Grant Scheme (17H62) and FRGS (4F786).

### Compliance with ethical standards

### Conflict of interest

The authors declare that they have no conflict of interest.

### Ethical approval

This paper does not contain any studies with human participants or animals performed by any of the authors.

### Informed consent

Informed consent was obtained from all individual participants included in the study.

## References

- Alcalá-Fdez J, Fernandez A, Luengo J, Derrac J, García S, Sánchez L, Herrera F (2011) KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. J Mult Valued Log Soft Comput 17(2–3):255–287Google Scholar
- Alia O, Mandava R (2011) The variants of the harmony search algorithm: an overview. Artif Intell Rev 36(1):49–68Google Scholar
- Amiri B, Hossain L, Mosavi SE (2010) Application of harmony search algorithm on clustering. In World congress on engineering and computer science, vols 1 and 2, pp 460–465Google Scholar
- Beheshti Z, Shamsuddin SM (2013) A review of population-based meta-heuristic algorithms. Int J Adv Soft Comput Appl 5(1):1–35Google Scholar
- Beheshti Z, Shamsuddin SMH (2014) CAPSO: centripetal accelerated particle swarm optimization. Inf Sci 258:54–79MathSciNetGoogle Scholar
- Bahesti Z, Shamsuddin SM, Hasan S (2013) MPSO: median oriented particle swarm optimization. Appl Math Comput 219:5817–5836MathSciNetzbMATHGoogle Scholar
- Beheshti Z, Shamsuddin SMH, Beheshti E, Yuhaniz SS (2014) Enhancement of artificial neural network learning using centripetal accelerated particle swarm optimization for medical diseases diagnosis. Soft Comput 18(11):2253–2270Google Scholar
- Brabazon A, O’Neill M (2006) Biologically inspired algorithms for financial modeling. Springer, BerlinzbMATHGoogle Scholar
- David HW, William GM (1997) No free lunch theorem for optimization. IEEE Trans Evolut Comput 1(1):67–82Google Scholar
- Geem ZW (2009a) Particle-swarm harmony search for water network design. Eng Optim 41(4):297–311Google Scholar
- Geem ZW (2009b) Music inspired harmony search algorithm: theory and applications. Springer, New YorkGoogle Scholar
- Geem ZW, Kim JH, Loganathan GV (2001) A new heuristic optimization algorithm: harmony search. Simulation 76(2):60–68Google Scholar
- Hasan S (2010) Enhanced self-organizing map with particle swarm optimization for classification problems. Master thesis, Universiti Teknologi MalaysiaGoogle Scholar
- Hasan S, Shamsuddin SM (2011) Multistrategy self-organizing map learning for classification problems. Comput Intell Neurosci 2011(121787):11. https://doi.org/10.1155/2011/121787 Google Scholar
- Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, Upper Saddle RiverzbMATHGoogle Scholar
- Jiming L, Tsui KC (2006) Toward nature-inspired computing. Commun ACM 49(10):59–64Google Scholar
- Kattan A, Abdullah R, Salam RA (2010) Harmony search based supervised training of artificial neural networks. In: UKSim-AMSS first international conference on intelligent systems, modelling and simulation, pp 105–110Google Scholar
- Kennedy J, Eberhart (1995) Particle swarm optimization. In: Proceedings of IEEE international conference on neural networks. IEEE Press, Piscataway, NJ, pp 1942–1948Google Scholar
- Kennedy J, Eberhart RC, Shi Y (2001) Swarm intelligence. Morgan Kaufmann, San FranciscoGoogle Scholar
- Kohonen T (2001) Self-organizing maps. Springer series in information sciences, vol 30, 3rd extended edition. Springer, BerlinGoogle Scholar
- Kulluk S, Ozbakir L, Baykasoglu A (2012) Training neural networks with harmony search algorithms for classification problems. Eng Appl Artif Intell 25(1):11–19Google Scholar
- Lee Anzy, Geem Zong Woo, Suh Kyung-Duck (2016) Determination of optimal weights of an artificial neural networks by using the harmony search algorithm: application to breakwater armor stones. Appl Sci 6(164):1–17Google Scholar
- Mahdavi M, Fesanghary M, Damangir E (2007) An improved harmony search algorithm for solving optimization problems. Appl Math Comput 188(2):1567–1579MathSciNetzbMATHGoogle Scholar
- Mahdavi M, Chehreghani MH, Abolhassani H, Forsati R (2008) Novel meta-heuristic algorithms for clustering web documents. Appl Math Comput 201(1–2):441–451MathSciNetzbMATHGoogle Scholar
- Michalski RS (1994) Machine learning: a multistrategy approach. In: Michalski RS, Tecuci G (eds) Inferential learning theory as conceptual basis for multistrategy learning, vol IV. Morgan Kaufmann Publishers, San MateoGoogle Scholar
- Negnevitsky M (2005) Artificial intelligence: a guide to intelligent systems, 2nd edn. Addison Wesley, HarlowGoogle Scholar
- Omran MGH, Mahdavi M (2008) Global-best harmony search. Appl Math Comput 198(2):643–656MathSciNetzbMATHGoogle Scholar
- O’Neill M, Brabazon A (2008) Self-organising swarm (SOSwarm). Soft Comput 12(11):1073–1080Google Scholar
- Ozcift A, Kaya M, Gulten A, Karabulut M (2009) Swarm optimized organizing map (SWOM): a swarm intelligence based optimization of self-organizing map. Expert Syst Appl 36(7):10640–10648Google Scholar
- Pan Q-K, SuganthanM PN, Tasgetiren F, Liang JJ (2010) A self-adaptive global best harmony search algorithm for continuous optimization problems. Appl Math Comput 216(3):830–848MathSciNetzbMATHGoogle Scholar
- Von der Malsburg C (1973) Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14:85–100Google Scholar
- Xiao X, Dow ER, Eberhart R, Miled ZB, Oppelt RJ (2003) Gene-clustering using self-organizing maps and particle swarm optimization. IEEE international parallel and distributed processing symposium (IPDPS). IEEE PressGoogle Scholar
- Xiao X, Dow ER, Eberhart R, Miled ZB, Oppelt RJ (2004) A hybrid self-organizing maps and particle swarm optimization approach. Concurr Comput Pract Exp 16(9):895–915Google Scholar
- Yang XS (2009) Music-inspired Harmony search algorithm. In: Geem Z (ed) Harmony search as a metaheuristic algorithm. Springer, Berlin, pp 1–14Google Scholar
- Yang XS (2010) Engineering optimization: an introduction with metaheuristic applications. Wiley, HobokenGoogle Scholar