Abstract
The exclusive-or (XOR) classification task still represents a challenge in the study of cognition since the precise neural circuit sustaining the general ability to learn nonlinear problems remains to be discovered in natural organisms. As such, this paper focuses on a neurorobotic application embedding a specific spiking neural network built to solve these types of tasks. This experiment proposes a 2-bit task (XOR) with visual compound binary images acting as inputs and a left/right action for the output. The robot learns to solve it in both virtual and real environments from an operant conditioning procedure. Furthermore, the robot also adapts its behavior from learning all other simpler associative rules, even when switching them at runtime. Finally, this study explores the impact on the neural architecture, when passing from a 2-bit to a 3-bit task.
Similar content being viewed by others
References
Behrends A, Scheiner R (2012) Octopamine improves learning in newly emerged bees but not in old foragers. J Exp Biol 215(7):1076–1083
Bi G, Poo M (1998) Activity-induced synaptic modifications in hippocampal culture: dependence on spike timing, synaptic strength and cell type. J Neurosci 18:10464–10472
Caporale N, Dan Y (2008) Spike timing-dependent plasticity: a Hebbian learning rule. Annu Rev Neurosci 31:25–46
Casacuberta D, Ayala S, Vallverdú J (2012) Embodying cognition: a morphological perspective. In: Machine learning: concepts, methodologies, tools and applications. IGI Global, pp 1798–1818
Cyr A, Boukadoum M, Poirier P (2009) Ai-SIMCOG: a simulator for spiking neurons and multiple animat’s behaviours. Neural Comput Appl 18(5):431–446
Cyr A, Boukadoum M, Thériault F (2014) Operant conditioning: a minimal components requirement in artificial spiking neurons designed for bio-inspired robot’s controller. Front Neurorobot 8:1–13
Deisig N, Lachnit H, Giurfa M, Hellstern F (2001) Configural olfactory learning in honeybees: negative and positive patterning discrimination. Learn Mem 8(2):70–78
El-Laithy K, Bogdan M (2011) A reinforcement learning framework for spiking networks with dynamic synapses. Comput Intell Neurosci 2011:4
Frémaux N, Sprekeler H, Gerstner W (2010) Functional requirements for reward-modulated spike-timing-dependent plasticity. J Neurosci 30(40):13326–13337
Gardner B, Sporea I, Grüning A (2015) Encoding spike patterns in multilayer spiking neural networks. arXiv preprint arXiv:1503.09129
Gerstner W, Kistler W (2002) Spiking neuron models: single neurons, populations, plasticity. Cambridge University Press, Cambridge
Ghosh-Dastidar S, Adeli H (2009) Spiking neural networks. Int J Neural Syst 19(04):295–308
Giurfa M, Zhang S, Jenett A, Menzel R, Srinivasan MV (2001) The concepts of ‘sameness’ and ‘difference’in an insect. Nature 410(6831):930–933
Grand C, Honey RC (2008) Solving XOR. J Exp Psychol Anim Behav Process 34(4):486
Hammer M (1997) The neural basis of associative reward learning in honeybees. Trends Neurosci 20(6):245–252
Izhikevich EM (2003) Simple model of spiking neurons. IEEE Trans Neural Netw 14(6):1569–1572
Jitsumori M, Ohkita M, Ushitani T (2011) The learning of basic-level categories by pigeons: the prototype effect, attention, and effects of categorization. Learn Behav 39(3):271
Krichmar JL (2018) Neurorobotics—a thriving community and a promising pathway toward intelligent cognitive robots. Front Neurorobot 12:42. https://doi.org/10.3389/fnbot.2018.00042
Maass W (1997) Networks of spiking neurons: the third generation of neural network models. Neural Netw 10(9):1659–1671
Markram H, Lubke J, Frotscher M, Sakmann B (1997) Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs. Science 275:213–215
Minsky M, Papert S (1969) An introduction to computational geometry. Cambridge tiass., HIT
Paul C (2006) Morphological computation: a basis for the analysis of morphology and control requirements. Robot Auton Syst 54(8):619–630
Pawlak V, Wickens JR, Kirkwood A, Kerr JN (2010) Timing is not everything: neuromodulation opens the STDP gate. Front Synaptic Neurosci 2:138
Pezzulo G, Barsalou LW, Cangelosi A, Fischer MH, Spivey M, McRae K (2011) The mechanics of embodiment: a dialog on embodiment and computational modeling. Front Psychol 2:5
Reljan-Delaney M, Wall J (2017) Solving the linearly inseparable XOR problem with spiking neural networks. In: 2017 computing conference. IEEE, pp 701–705
Rumelhart DE, Hinton GE, Williams RJ (1988) Learning representations by back-propagating errors. Cognit Model 5(3):1
Schultz W (1998) Predictive reward signal of dopamine neurons. J Neurophysiol 80(1):1–27
Seung HS (2003) Learning in spiking neural networks by reinforcement of stochastic synaptic transmission. Neuron 40(6):1063–1073
Smith JD, Coutinho MV, Couchman JJ (2011) The learning of exclusive-or categories by monkeys (Macaca mulatta) and humans (homo sapiens). J Exp Psychol Anim Behav Process 37(1):20
Unoki S, Matsumoto Y, Mizunami M (2006) Roles of octopaminergic and dopaminergic neurons in mediating reward and punishment signals in insect visual learning. Eur J Neurosci 24(7):2031–2038
Vassiliades V, Christodoulou C (2016) Behavioral plasticity through the modulation of switch neurons. Neural Netw 74:35–51
Zbeda R, Nathan P (2005) Multilayer neural network with back propagation: hardware solution to learning XOR. J Comput Sci Coll 20(5):144–146
Zeigler B, Muzy A (2017) Temporal modeling of neural net input/output behaviors: the case of XOR. Systems 5(1):7
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cyr, A., Thériault, F. & Chartier, S. Revisiting the XOR problem: a neurorobotic implementation. Neural Comput & Applic 32, 9965–9973 (2020). https://doi.org/10.1007/s00521-019-04522-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04522-0