Abstract
Learning is an important talent for understanding the nature and accordingly controlling behavioral characteristics. Behavioral learning theories are one of the popular learning theories which are built on experimental findings. These theories are widely applied in psychotherapy, psychology, neurology as well as in advertisements and robotics. There is an abundant literature associated with understanding learning mechanism, and various models have been proposed for the realization of learning theories. Nevertheless, none of those models are able to satisfactorily simulate the concept of classical conditioning. In this study, popular behavioral learning theories were firstly simplified and the contentious issues with them were clarified by conducting intuitive experiments. The experimental results and information available in the literature were evaluated, and behavioral learning theories were jointly generalized accordingly. The proposed model, to our knowledge, is the first one that possesses not only modeling all features of classical conditioning but also including all features with behavioral theories such as Pavlov, Watson, Guthrie, Thorndike and Skinner. Also, a microcontroller card (Arduino Mega 2560) was used to validate the applicability of the proposed model in robotics. Obtained results showed that this generalized model has a high capacity for modeling human learning. Then, the proposed learning model was further improved to be utilized as a machine learning method that can continuously learn similar to human being. The result obtained from the use of this method, in terms of computational cost and accuracy, showed that the proposed method can be successfully employed in machine learning, especially for time ordered datasets.
Similar content being viewed by others
References
Åsli O, Flaten MA (2008) Conditioned facilitation of the unconditioned reflex after classical eyeblink conditioning. Int J Psychophysiol 67:17–22. doi:10.1016/j.ijpsycho.2007.09.003
Vervliet B, Geens M (2014) Fear generalization in humans: impact of feature learning on conditioning and extinction. Neurobiol Learn Mem 113:143–148. doi:10.1016/j.nlm.2013.10.002
Shechner T, Hong M, Britton JC, Pine DS, Fox NA (2014) Fear conditioning and extinction across development: evidence from human studies and animal models. Biol Psychol 100:1–12. doi:10.1016/j.biopsycho.2014.04.001
Nokia MS, Penttonen M, Korhonen T, Wikgren J (2008) Hippocampal theta (3–8 Hz) activity during classical eyeblink conditioning in rabbits. Neurobiol Learn Mem 90:62–70. doi:10.1016/j.nlm.2008.01.005
Delamater AR, Westbrook RF (2014) Psychological and neural mechanisms of experimental extinction: a selective review. Neurobiol Learn Mem 108:38–51. doi:10.1016/j.nlm.2013.09.016
Todd TP, Vurbic D, Bouton ME (2014) Behavioral and neurobiological mechanisms of extinction in Pavlovian and instrumental learning. Neurobiol Learn Mem 108:52–64. doi:10.1016/j.nlm.2013.08.012
Bouton ME, Moody EW (2004) Memory processes in classical conditioning. Neurosci Biobehav Rev 28:663–674. doi:10.1016/j.neubiorev.2004.09.001
Aguado L (2003) Neuroscience of Pavlovian conditioning: a brief review. Span J Psychol 6(2):155–167. doi:10.1017/S1138741600005308
Hesslow G, Jirenhed D-A, Rasmussen A, Johansson F (2013) Classical conditioning of motor responses: what is the learning mechanism? Neural Netw 47:81–87. doi:10.1016/j.neunet.2013.03.013
Pavlov IP (1927) Conditioned reflexes. Dover Publications, New York
Dalla C, Shors TJ (2009) Sex differences in learning processes of classical and operant conditioning. Physiol Behav 97:229–238. doi:10.1016/j.physbeh.2009.02.035
Schunk DH (2012) Learning theories an educational perspective, 6th edn. Pearson, London
Watson JB (1913) Psychology as the behaviorist views it. Psychol Rev 20(2):158. doi:10.1037/h0074428
Inderbitzin M, Herreros-Alonso I, Verschure PFMJ (2010) An integrated computational model of the two phase theory of classical conditioning. IEEE. doi:10.1109/ijcnn.2010.5596874
Clouse RL, Kim S, Waldron MB (1997) An adaptive threshold learning algorithm for classical conditioning. In: Proceedings of the 19th international conference of the IEEE/EMBS, Chicago, pp 1380–1382
Malaka R, Hammer M (1996) Real-time models of classical conditioning. In: IEEE international conference on neural networks, vol 2. doi:10.1109/icnn.1996.548993
Allen CT, Madden TJ (1985) A closer look at classical conditioning. J Consum Res 12(3):301–315. doi:10.1086/208517
Li G, Quirk GJ, Nair SS (2007) Modeling acquisition and extinction of conditioned fear in LA neurons using learning algorithm. In: Proceedings of the 2007 American control conference Marriott Marquis Hotel at Times Square New York City, USA, pp 552–557. doi:10.1109/acc.2007.4283135
Prueckl R, Taub AH, Herreros I, Hogri R, Magal A, Bamford SA, Giovannucci A, Ofek R, Shacham-Diamand Y, Verschure PFMJ, Mintz M, Scharinger J, Silmon A, Guger C (2011) Behavioral rehabilitation of the eye closure reflex in senescent rats using a real-time biosignal acquisition system. In: 33rd annual international conference of the IEEE EMBS, Boston, Massachusetts, USA, pp 4211–4214. doi:10.1109/iembs.2011.6091045
Courville AC, Daw ND, Gordon GJ, Touretzky DS (2003) Model uncertainty in classical conditioning. In: 17th annual conference on advances in neural information processing systems (NIPS), Vancouver, BC, Canada
Austermann A, Yamada S (2008) Learning to understand multimodal rewards for human–robot-interaction using hidden Markov Models and classical conditioning. In: 2008 IEEE congress on evolutionary computation (CEC), pp 4096–4103. doi:10.1109/CEC.2008.4631356
Hassan H, Watan M (2000) On mathematical analysis of Pavlovian conditioning learning process using artificial neural network model. In: 10th mediterranean electrotechnical conference, MEleCon, vol II, pp 578–581. doi:10.1109/MELCON.2000.879999
Sutton RS, Barto AG (1981) Toward a modern theory of adaptive networks: expectation and prediction. Psychol Rev 88(2):135. doi:10.1037/0033-295x.88.2.135
Wagner AR (1981) SOP: a model of automatic memory processing in animal behavior. In: Spear NE, Miller RR (eds) Information processing in animals: memory mechanisms, chapter 1, vol 85. Erlbaum, New Jersey, pp 5–44
Sutton RS, Barto AG (1990) Time-derivative models of Pavlovian reinforcement. In: Gabriel A, Moore J (eds) Learning and computational neuroscience: foundations and adaptive networks, chapter 12. MIT Press, Cambridge, pp 497–537
Klopf AH (1989) Classical conditioning: phenomena predicted by a drive-reinforcement model of neural function. In: Byrne JH, Berry WO (eds) Neural models of plasticity: experimental and theoretical approaches, chapter 6. Academic Press, New York, pp 94–103. doi:10.1016/B978-0-12-148955-7.50011-4
Balkenius C, Moren J (1999) Dynamics of a classical conditioning model. Auton Robots 7:41–56. doi:10.1023/A:1008965713435
Malaka R, Lange R, Hammer M (1995) A constant prediction model for classical conditioning. In: Elser N, Menzel R (eds) Learning and memory: proceedings of the 23rd Gottingen neurobiology conference, vol 1. Thieme-Verlag, Stuttgart, p 75
Balkenius C, Morén J (1998) Computational models of classical conditioning: a comparative study. In: Proceedings of the fifth international conference on simulation of adaptive behavior on from animals to animats, vol 5
Klopf AH (1988) A neuronal model of classical conditioning. Psychobiology 16(2):85–125
Liu S, Ding Y (2008) An adaptive network policy management framework based on classical conditioning. In: Proceedings of the 7th world congress on intelligent control and automation, Chongqing, China, pp 3336–3340. doi:10.1109/WCICA.2008.4593455
Liu S, Ding Y (2009) A classical conditioning model for policy-based management. In: 2009 international conference on networks security, wireless communications and trusted computing, pp 249–252. doi:10.1109/NSWCTC.2009.129
Ertugrul OF, Tagluk ME (2014) Learning with classical conditioning. In: Signal processing and communications applications conference (SIU), 2014 22nd. IEEE, pp 927–930. doi:10.1109/SIU.2014.6830382
Chester DL (1990) A comparison of some neural network models of classical conditioning. In: IEEE, pp 1163–1168. doi:10.1109/isic.1990.128601
Vogel EH, Castro ME, Saavedra MA (2004) Quantitative models of Pavlovian conditioning. Brain Res Bull 63:173–202. doi:10.1016/j.brainresbull.2004.01.005
Malaka R (1999) Models of classical conditioning models of classical conditioning. Bull Math Biol 61:33–83, Article No. bulm.1998.0074
Watson JB, Rayner R (1920) Little Emotional Albert, Conditioned emotional responses. J Exp Psychol 3:1–14. doi:10.1037/h0069608
Watson JB (1959) Behaviorism. University of Chicago Press, Chicago, p 82
Voeks VW (1950) Formalization and clarification of a learning of theory. J Psychol 30:341–362. doi:10.1080/00223980.1950.9916072
Guthrie ER (1934) Reward and punishment. Psychol Rev 41:450–460. doi:10.1037/h0074245
Guthrie ER (1946) Psychological facts and psychological theory. Psychol Bull 43:1–20. doi:10.1037/h0061712
Hassan HM, Al-Hamadi A (2008) On comparative evaluation of Thorndike’s psycho-learning experimental work versus an optimal swarm ıntelligent system. In: CIMCA 2008, IAWTIC 2008, and ISE 2008, IEEE Computer Society, syf., pp 1083–1088. doi:10.1109/CIMCA.2008.224
Skinner BF (2013) A life [paperback]. by Daniel W. Bjork: 9781557984166: Amazon.com: Books
Schmajuk NA, Szymanski WA, Weaver EA (1999) Adaptive communication in animals and robots. Sig Process 74:71–87. doi:10.1016/S0165-1684(98)00203-5
Huitt W, Hummel J (1997) An introduction to operant (instrumental) conditioning. In: Educational psychology interactive. Valdosta State University, Valdosta. Retrieved [date] from http://www.edpsycinteractive.org/topics/behsys/operant.html
Gaudiano P, Chang C (1997) Adaptive obstacle avoidance with a neural network for operant conditioning: experiments with real robots. In: IEEE, pp 13–18. doi:10.1109/cira.1997.613832
Ruan X, Ren H (2009) Bionic learning algorithm based on Skinner’s operant conditioning and control of robot. In: IEEE Computer Society, 2009 WASE international conference on information engineering, pp 62–66. doi:10.1109/ICIE.2009.143
Ruan X, Dai L (2010) Skinner-rat experiment based on autonomous operant conditioning automata. In: Sixth international conference on natural computation (ICNC 2010), IEEE circuits and systems society, pp 1970-1973. doi:10.1109/ICNC.2010.5584702
Ren H, Ruan X (2009) Applying of recurrent network based on Skinner’s operant conditioning in robot. In: 2009 international conference on intelligent human-machine systems and cybernetics, IEEE, syf., pp 351–354. doi:10.1109/ihmsc.2009.96
Cai J, Ruan X (2009) Self-balance control of inverted pendulum based on fuzzy skinner operant conditioning. Int Conf Inf Technol Comput Sci 2009:518–521. doi:10.1109/ITCS.2009.241
Morgan JS, Patterson EC, Klopf AH (1990) A drive-reinforcement neural network model of simple instrumental conditioning. IJCNN Int Joint Conf IEEE. doi:10.1109/ijcnn.1990.137719
Morris MJ (2000) The Artie simulation of operant conditioning. Mex J Behav Anal 26:251–271
Kamin LJ (1968) Attention-like processes in classical conditioning. In: Jones MR (ed) Miami symposium on the prediction of behavior: aversive stimulation. University of Miami Press, Miami, pp 9–31
Rescorla RA (1968) Probability of shock in the presence and absence of CS in fear conditioning. J Comp Physiol Psychol 66:1–5. doi:10.1037/h0025984
Garcia J, Koelling RA (1966) Relation of cue to consequences in avoidance learning. Psychon Sci 4:123–124. doi:10.3758/BF03342209
Hughes JR (1958) Post-tetanic potentiation. Physiol Rev 38(1):91–113
Alvarez O, Gonzalez C, Latorre R (2012) Counting channels: a tutorial guide on ion channel fluctuation analysis. Adv Physiol Educ 26:327–341. doi:10.1152/advan.00006.2002
Hebb DO (1961) Distinctive features of learning in the higher animal. In: Delafresnaye JF (ed) Brain mechanisms and learning. Oxford University Press, London
Drucker H, Burges CJ, Kaufman L, Smola A, Vapnik V (1997) Support vector regression machines. Neural Inf Process Syst 9:155–161
Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501. doi:10.1016/j.neucom.2005.12.126
Bache K, Lichman M (2013) UCI machine learning repository. http://archive.ics.uci.edu/ml. University of California, School of Information and Computer Science, Irvine
Smith JW, Everhart JE, Dickson WC, Knowler WC, Johannes RS (1988) Using the ADAP learning algorithm to forecast the onset of diabetes mellitus. In: Proceedings/the annual symposium on computer application [sic] in medical care. symposium on computer applications in medical care, American Medical Informatics Association, pp 261–265
Ramana BV, Babu P, Surendra M, Venkateswarlu NB (2011) A critical study of selected classification algorithms for liver disease diagnosis. Int J Database Manag Syst 3(2):101–114. doi:10.5121/ijdms.2011.3207
Ramana BV, Babu MSP, Venkateswarlu NB (2012) A critical comparative study of liver patients from USA and INDIA: an exploratory analysis. Int J Comput Sci Issues IJCSI 9(3):506–516
Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE (2001) Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. Phys Rev E 64(6):061907-1–061907-8. doi:10.1103/PhysRevE.64.061907
Wettschereck D, Dietterich TG (1995) An experimental comparison of the nearest-neighbor and nearest-hyperrectangle algorithms. Mach Learn 19(1):5–27. doi:10.1007/BF00994658
Read J, Bifet A, Pfahringer B, Holmes G (2012) Batch-incremental versus instance-incremental learning in dynamic and evolving data. In: Advances in intelligent data analysis XI, Springer, Berlin, pp 313–323. doi:10.1007/978-3-642-34156-4_29
Cunningham P, Delany SJ (2007) k-Nearest neighbour classifiers. Technical Report UCD-CSI-2007-4, Artificial Intelligence Group, Dublin, pp 1–17
Ade RR, Ghriet P, Deshmukh PR, Scoe TA (2013) Methods for incremental learning: a survey. Int J Data Min Knowl Manag Process 3(4):119–125. doi:10.5121/ijdkp.2013.3408
Duan D, Li Y, Li R, Lu Z (2012) Incremental K-clique clustering in dynamic social networks. Artif Intell Rev 38(2):129–147. doi:10.1007/s10462-011-9250-x
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ertuğrul, Ö.F., Tağluk, M.E. A novel machine learning method based on generalized behavioral learning theory. Neural Comput & Applic 28, 3921–3939 (2017). https://doi.org/10.1007/s00521-016-2314-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2314-8