Competitive Brain Emotional Learning

Abstract

Brain emotional learning (BEL) methods are a recently developed class of emotional brain-inspired algorithms, that enjoy feed-forward computational complexity on the order of O(n). BEL methods suffer from a major drawback related to the non-linear problem solving ability, i.e. they cannot solve n-bit parity problems in which \(\hbox {n} \ge 3\). The present paper proposes a competitive BEL (C-BEL) capable of accommodating a higher number of bits in the parity problem. The proposed C-BEL is inspired by the competitive property of neucortex’s neurocircuits. The method is tested on n-bit parity, function approximation and a pattern recognition problem. Various comparisons with the reinforcement BEL (R-BEL), supervised BEL (S-BEL), evolutionary BEL (E-BEL), a Boltzmann machine and a convolutional neural network indicate the superiority of the approach in terms of its higher ability in non-linear problem solving, function approximation and pattern recognition.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

References

  1. 1.

    Abdi J, Moshiri B, Abdulhai B, Sedigh AK (2011) Forecasting of short-term traffic flow based on improved neuro-fuzzy models via emotional temporal difference learning algorithm. Eng Appl Artif Intell. doi:10.1016/j.engappai.2011.09.011

    Google Scholar 

  2. 2.

    Abu-Mostafa YS, St Jacques J (1985) Information capacity of the Hopfield model. IEEE Trans Inf Theory 31(4):461–464

    Article  MATH  Google Scholar 

  3. 3.

    Amin MF, Savitha R, Amin MI, Murase K (2012) Orthogonal least squares based complex-valued functional link network. Neural Netw 32:257–266

    Article  Google Scholar 

  4. 4.

    Asad M, Farooq U, Gu J, Amin J, Sadaqat A, El-Hawary M, Luo J (2017) Neo-fuzzy supported brain emotional learning based pattern recognizer for classification problems. IEEE Access 5:6951–6967

    Article  Google Scholar 

  5. 5.

    Aylett R, Louchart S, Dias J, Paiva A, Vala M (2005) FearNot!—an experiment in emergent narrative. In: Intelligent virtual agents, Springer Berlin/Heidelberg pp 305–316

  6. 6.

    Babaie T, Karimizandi R, Lucas C (2008) Learning based brain emotional intelligence as a new aspect for development of an alarm system. Soft Comput 12(9):857–873

    Article  Google Scholar 

  7. 7.

    Balkenius C, Morén J (2001) Emotional learning: a computational model of AMYG. Cybern Syst 32(6):611–636

    Article  MATH  Google Scholar 

  8. 8.

    Beheshti Z, Hashim SZM (2010) A review of emotional learning and it’s utilization in control engineering. Int J Adv Soft Comput Appl 2:191–208

    Google Scholar 

  9. 9.

    Bianchin M, Mello e Souza T, Medina JH, Izquierdo I (1999a) The AMYG is involved in the modulation of long-term memory, but not in working or short-term memory. Neurobiol Learn Mem 71(2):127–131

    Article  Google Scholar 

  10. 10.

    Binas J, Rutishauser U, Indiveri G, Pfeiffer M (2014) Learning and stabilization of winner-take-all dynamics through interacting excitatory and inhibitory plasticity. Front Comput Neurosci 8:429

    Article  Google Scholar 

  11. 11.

    Carpenter GA, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comput Vis Gr Image Process 37(1):54–115

    Article  MATH  Google Scholar 

  12. 12.

    César MB, Gonçalves J, Coelho J, de Barros RC (2017) Brain emotional learning based control of a SDOF structural system with a MR damper. In: Garrido P, Soares F, Moreira A (eds) CONTROLO 2016. Lecture notes in electrical engineering, vol 402. Springer, Cham, pp 547–557

  13. 13.

    Chandra M (2005) Analytical study of a control algorithm based on emotional processing, M.S. Dissertation, Indian Institute of Technology Kanpur

  14. 14.

    Coultrip R, Granger R, Lynch G (1992) A cortical model of winner-take-all competition via lateral inhibition. Neural Netw 5(1):47–54

    Article  Google Scholar 

  15. 15.

    Dai Q (2013a) A competitive ensemble pruning approach based on cross-validation technique. Knowl Based Syst 37:394–414

    Article  Google Scholar 

  16. 16.

    Dai Q (2013b) Back-propagation with diversive curiosity: an automatic conversion from search stagnation to exploration. Appl Soft Comput 13(1):483–495

    Article  Google Scholar 

  17. 17.

    Dai Q, Song G (2016) A novel supervised competitive learning algorithm. Neurocomputing 191:356–362

    Article  Google Scholar 

  18. 18.

    Daryabeigi E, Markadeh GRA, Lucas C (2010) Emotional controller (BELBIC) for electric drives—a review, 7–10 Nov., Glendale, AZ, pp 2901–2907, doi:10.1109/IECON.2010.5674934

  19. 19.

    Dehkordi BM, Kiyoumarsi A, Hamedani P, Lucas C (2011a) A comparative study of various intelligent based controllers for speed control of IPMSM drives in the field-weakening region. Expert Syst Appl 38(10):12643–12653

    Article  Google Scholar 

  20. 20.

    Dehkordi BM, Parsapoor A, Moallem M, Lucas C (2011b) Sensorless speed control of switched reluctance motor using brain emotional learning based intelligent controller. Energy Convers Manag 52(1):85–96

    Article  Google Scholar 

  21. 21.

    Dehuri S, Cho SB (2010) Evolutionarily optimized features in functional link neural network for classification. Expert Syst Appl 37(6):4379–4391

    Article  Google Scholar 

  22. 22.

    Dehuri S, Roy R, Cho SB, Ghosh A (2012) An improved swarm optimized functional link artificial neural network (ISO-FLANN) for classification. J Syst Softw 85(6):1333–1345

    Article  Google Scholar 

  23. 23.

    Douglas Rodney J, Martin Kevan AC (2004) Neuronal circuits of the neocortex. Annu Rev Neurosci 27:419–451

    Article  Google Scholar 

  24. 24.

    El-Saify MH, El-Garhy AM, El-Sheikh GA (2017) Brain Emotional Learning Based Intelligent Decoupler for Nonlinear Multi-Input Multi-Output Distillation Columns. Math Probl Eng. doi:10.1155/2017/8760351

    Google Scholar 

  25. 25.

    Fadok JP, Darvas M, Dickerson TM, Palmiter RD (2010) Long-term memory for pavlovian fear conditioning requires dopamine in the nucleus accumbens and basolateral AMYG. PLoS ONE 5(9):e12751

    Article  Google Scholar 

  26. 26.

    Farhoudi Z, Setayeshi S, Rabiee A (2017) Using learning automata in brain emotional learning for speech emotion recognition. Int J Speech Technol. doi:10.1007/s10772-017-9426-0

    Google Scholar 

  27. 27.

    Fino E, Yuste R (2011) Dense inhibitory connectivity in neocortex. Neuron 69(6):1188–1203

    Article  Google Scholar 

  28. 28.

    Gholipour A, Lucas C, Shahmirzadi D (2004) Predicting geomagnetic activity index by brain emotional learning. WSEAS Trans Syst 3m:296–299

    Google Scholar 

  29. 29.

    Goleman D (2006) Emotional intelligence; why it can matter more than IQ, Bantam

  30. 30.

    Griggs EM, Young EJ, Rumbaugh G, Miller CA (2013) MicroRNA-182 regulates AMYG-dependent memory formation. J Neurosci 33(4):1734–1740

    Article  Google Scholar 

  31. 31.

    Grossberg S, Seidman D (2006) Neural dynamics of autistic behaviors: cognitive, emotional, and timing substrates. Psychol Rev 113:483–525

    Article  Google Scholar 

  32. 32.

    Guyton AC, Hall JE (2010) Textbook of medical physiology: enhanced e-book. Elsevier, Amsterdam

    Google Scholar 

  33. 33.

    Hardt O, Nader K, Nadel L (2013) Decay happens: the role of active forgetting in memory. Trends Cogn Sci 17(3):111–120

    Article  Google Scholar 

  34. 34.

    Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254–1259

    Article  Google Scholar 

  35. 35.

    Jafarzadeh S (2008) Designing PID and BELBIC controllers in path tracking problem. Int J Comput Commun Control, ISSN 1841-9836, E-ISSN 1841-9844, Vol. III (2008), Suppl. issue: Proceedings of ICCCC 2008, pp 343–348

  36. 36.

    Kalayci TE, Bahrepour M, Meratnia N, Havinga PJ (2011) How wireless sensor networks can benefit from brain emotional learning based intelligent controller (BELBIC). Proc Comput Sci 5:216–223

    Article  Google Scholar 

  37. 37.

    Khalilian M, Abedi A, Zadeh AD (2012) Position control of hybrid stepper motor using brain emotional controller. Energy Proced 14:1998–2004

    Article  Google Scholar 

  38. 38.

    Kim JH, Li S, Hamlin AS, McNally GP, Richardson R (2011) Phosphorylation of mitogen-activated protein kinase in the medial prefrontal cortex and the AMYG following memory retrieval or forgetting in developing rats. Neurobiol Learn Mem 97(1):59–68

    Article  Google Scholar 

  39. 39.

    Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480

    Article  Google Scholar 

  40. 40.

    LeDoux JE (1991) Emotion and the limbic system concept. Concepts Neurosci 2:169–199

    Google Scholar 

  41. 41.

    LeDoux J (1996) The emotional brain. Simon and Schuster, New York

    Google Scholar 

  42. 42.

    LeDoux JE (2000) Emotion circuits in the brain. Annu Rev Neurosci 23(1):155–184

    MathSciNet  Article  Google Scholar 

  43. 43.

    Levine DS (2007) Neural network modeling of emotion. Phys Life Rev 4(1):37–63

    Article  Google Scholar 

  44. 44.

    Li S, Liu B, Li Y (2013) Selective positive-negative feedback produces the winner-take-all competition in recurrent neural networks. IEEE Trans Neural Netw Learn Syst 24(2):301–309

    MathSciNet  Article  Google Scholar 

  45. 45.

    Lin BS, Lin BS, Chong FC, Lai F (2006) A functional link network with higher order statistics for signal enhancement. IEEE Trans Signal Process 54(12):4821–4826

    Article  MATH  Google Scholar 

  46. 46.

    Lotfi E, Akbarzadeh TMR (2013a) Brain emotional learning-based pattern recognizer. Cybern Syst 44(5):402–421

    Article  Google Scholar 

  47. 47.

    Lotfi E, Akbarzadeh TMR (2014a) Adaptive brain emotional decayed learning for online prediction of geomagnetic activity indices. Neurocomputing 126:188–196

    Article  Google Scholar 

  48. 48.

    Lotfi E, Akbarzadeh TMR (2014) Practical emotional neural networks. Neural Netw. doi:10.1016/j.neunet.2014.06.012

    Google Scholar 

  49. 49.

    Lotfi E, Akbarzadeh TMR (2016) A winner-take-all approach to emotional neural networks with universal approximation property. Inf Sci 346:369–388

    Article  Google Scholar 

  50. 50.

    Lotfi E, Keshavarz A (2014d) Gene expression microarray classification using PCA-BEL. Comput Biol Med 54:180–187

    Article  Google Scholar 

  51. 51.

    Lotfi E, Rezaee AA (2017) A competitive functional link artificial neural network as a universal approximator. Soft Comput. doi:10.1007/s00500-017-2644-1

    Google Scholar 

  52. 52.

    Lotfi E, Setayeshi S, Taimory S (2014c) A neural basis computational model of emotional brain for online visual object recognition. Appl Artif Intell 28(8):814–834

    Article  Google Scholar 

  53. 53.

    Lotfi E, Akbarzadeh T M R (2013b) Emotional brain-inspired adaptive fuzzy decayed learning for online prediction problems. In: 2013 IEEE international conference on Fuzzy systems (FUZZ), pp 1–7. IEEE

  54. 54.

    Lucas C (2011) BELBIC and its industrial applications: towards embedded neuroemotional control code sign. In: Integrated systems, design and technology 2010, Springer Berlin Heidelberg, pp 203–214

  55. 55.

    Lucas C, Shahmirzadi D, Sheikholeslami N (2004) Introducing BELBIC: brain emotional learning based intelligent controller. Int J Intell Autom Soft Comput 10:11–21

    Article  Google Scholar 

  56. 56.

    Lumer ED (2000) Effects of spike timing on winner-take-all competition in model cortical circuits. Neural Comput 12(1):181–194

    Article  Google Scholar 

  57. 57.

    Marinier R, Laird JE (2008) Emotion-driven reinforcement learning. Cognitive Science, 115-120

  58. 58.

    Marsella SC, Gratch J (2009) EMA: a process model of appraisal dynamics. Cogn Syst Res 10(1):70–90

    Article  Google Scholar 

  59. 59.

    Mehrabian AR, Lucas C (2005) Emotional learning based intelligent robust adaptive controller for stable uncertain nonlinear systems. Int J Eng Math Sci 2(4):246–252

    Google Scholar 

  60. 60.

    Mehrabian AR, Lucas C, Roshanian J (2006) Aerospace launch vehicle control: an intelligent adaptive approach. Aerosp Sci Technol 10(2):149–155

    Article  MATH  Google Scholar 

  61. 61.

    Mei Y, Tan G, Liu Z (2017) An improved brain-inspired emotional learning algorithm for fast classification. Algorithms 10(2):70

    MathSciNet  Article  Google Scholar 

  62. 62.

    Milad HS, Farooq U, El-Hawary ME, Asad MU (2017) Neo-fuzzy integrated adaptive decayed brain emotional learning network for online time series prediction. IEEE Access 5:1037–1049

    Article  Google Scholar 

  63. 63.

    Misra BB, Dehuri S (2007) Functional link artificial neural network for classification task in data mining. J Comput Sci 3(12):948

    Article  Google Scholar 

  64. 64.

    Moghadam Ahmadi R, Yaghoubi M (2015) Interval emotional neural network for prediction of Kp, AE and Dst geomagnetic activity indices. In: 2015 international congress on technology, communication and knowledge (ICTCK), pp 325–331. IEEE

  65. 65.

    Morén J (2002) Emotion and learning—a computational model of the AMYG. Ph.D. Thesis, Department of Cognitive Science, Lund University, Lund, Sweden

  66. 66.

    Morén J, Balkenius C (2000) A computational model of emotional learning in the AMYG. In: , Meyer JA, Berthoz A, Floreano D, Roitblat HL, Wilson SW (Eds.) from animals to animats 6: Proceedings of the 6th international conference on the simulation of adaptive behaviour MIT Press, Cambridge, MA., USA., pp 115–124

  67. 67.

    Motamed S, Setayeshi S, Rabiee A (2017) Speech emotion recognition based on a modified brain emotional learning model. Biol Inspir Cogn Archit 19:32–38. doi:10.1016/j.bica.2016.12.002

    Google Scholar 

  68. 68.

    Oster M, Douglas R, Liu SC (2009) Computation with spikes in a winner-take-all network. Neural Comput 21(9):2437–2465

    MathSciNet  Article  MATH  Google Scholar 

  69. 69.

    Palm G, Sommer FT (1992) Information capacity in recurrent McCulloch-Pitts networks with sparsely coded memory states. Network Comput Neural Syst 3(2):177–186

    Article  MATH  Google Scholar 

  70. 70.

    Peri RM, Mandal P, Haque AU, Tseng B (2015) Very short-term prediction of wind farm power: an advanced hybrid intelligent approach. In: Industry applications society annual meeting, 2015 IEEE, pp 1–8 IEEE

  71. 71.

    Pessoa L (2008) On the relationship between emotion and cognition. Nat Rev Neurosci 9(2):148–158

    Article  Google Scholar 

  72. 72.

    Pessoa L (2009) How do emotion and motivation direct executive control? Trends Cogn Sci 13(4):160–166

    Article  Google Scholar 

  73. 73.

    Raymundo CR, Johnson CG, Vargas PA (2015, August) An architecture for emotional and context-aware associative learning for robot companions. In: 2015 24th IEEE International Symposium on robot and human interactive communication (RO-MAN), pp 31–36. IEEE

  74. 74.

    Riesenhuber M, Poggio T (1999) Hierarchical models of object recognition in cortex. Nat Neurosci 2(11):1019–1025

    Article  Google Scholar 

  75. 75.

    Rizzi C, Johnson CG, Fabris F, Vargas PA (2016) A situation-aware fear learning (SAFEL) model for robots. Neurocomputing

  76. 76.

    Rolls ET (1992) Neurophysiology and functions of the primate AMYG. In: The AMYG: neurobiologycal aspects of emotion, memory and mental dysfunction

  77. 77.

    Rouhani H, Jalili M, Araabi BN, Eppler W, Lucas C (2007) Brain emotional learning based intelligent controller applied to neurofuzzy model of micro-heat exchanger. Expert Syst Appl 32(3):911–918

    Article  Google Scholar 

  78. 78.

    Saabni R (2016) Recognizing handwritten single digits and digit strings using deep architecture of neural networks. In: International conference on artificial intelligence and pattern recognition (AIPR), pp 1–6. IEEE

  79. 79.

    Sadeghieh A, Sazgar H, Goodarzi K, Lucas C (2012) Identification and real-time position control of a servo-hydraulic rotary actuator by means of a neurobiologically motivated algorithm. ISA Trans 51(1):208–219

    Article  Google Scholar 

  80. 80.

    Sharma MK, Kumar A (2015) Performance comparison of brain emotional learning-based intelligent controller (BELBIC) and PI controller for continually stirred tank heater (CSTH). In: Computational Advancement in Communication Circuits and Systems, pp 293–301. Springer India

  81. 81.

    Sierra A, Macias JA, Corbacho F (2001) Evolution of functional link networks. IEEE Trans Evol Comput 5(1):54–65

    Article  Google Scholar 

  82. 82.

    Simard PY, Steinkraus D, Platt JC (2003) Best practices for convolutional neural networks applied to visual document analysis. In: ICDAR Vol. 3, pp 958–962

  83. 83.

    Tomczak JM, Gonczarek A (2016) Learning invariant features using subspace restricted Boltzmann machine. Neural Process Lett 1–10

  84. 84.

    Tsotsos JK, Culhane SM, Wai WYK, Lai Y, Davis N, Nuflo F (1995) Modeling visual attention via selective tuning. Artif Intell 78(1):507–545

    Article  Google Scholar 

  85. 85.

    Valipour MH, Maleki KN, Ghidary SS (2015) Optimization of emotional learning approach to control systems with unstable equilibrium. In: Lee R (ed) Software engineering, artificial intelligence, networking and parallel/distributed computing. Studies in computational intelligence, vol 569. Springer, Cham, pp 45–56

  86. 86.

    Vargas-Clara A, Redkar S (2015) Unmanned ground vehicle navigation using brain emotional learning based intelligent controller (BELBIC). Smart Sci 3(1):10–15

    Article  Google Scholar 

  87. 87.

    von der Malsburg Chr (1973) Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14(2):85–100

    Article  Google Scholar 

  88. 88.

    Wang X, Peng Q, Fan Y (2016) Detecting susceptibility to breast cancer with SNP-SNP interaction using BPSOHS and emotional neural networks. BioMed Res Int

  89. 89.

    Wu A, Zeng Z, Chen J (2014) Analysis and design of winner-take-all behavior based on a novel memristive neural network. Neural Comput Appl 24(7–8):1595–1600

    Article  Google Scholar 

Download references

Acknowledgements

The author greatly acknowledge support by the Islamic Azad University of Torbat-e-Jam under grant SAL-E-1394.

Author information

Affiliations

Authors

Corresponding author

Correspondence to E. Lotfi.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lotfi, E., Khazaei, O. & Khazaei, F. Competitive Brain Emotional Learning. Neural Process Lett 47, 745–764 (2018). https://doi.org/10.1007/s11063-017-9680-9

Download citation

Keywords

  • Amygdala
  • OFC
  • BELBIC
  • Emotional neural network