This work investigates adaptive behaviours for an intelligent robotic agent when subjected to temporal stimuli consisting of associations of contextual cues and simple reflexes. This is made possible thanks to a novel learning rule based on spike-timing-dependent plasticity and embedded in an artificial spiking neural network serving as a brain-like controller. The subsequent bio-inspired cognitive system carries out different classical conditioning tasks in a controlled virtual 3D-world while the timing and frequency of unconditioned and conditioned parameters are varied. The results of this simulated robotic environment are analysed at different stages from stimuli capture to neural spike generation and show extended behavioural capabilities by the robot in the temporal domain.
AbrahamW. C. (2003). How long will long-term potentiation last?Philosophical Transactions of the Royal Society of London B, 358, 735–744.
2.
AlnajjarF.MuraseK. (2008). A simple aplysia-like spiking neural network to generate adaptive behavior in autonomous robots. Adaptive Behavior, 16(5), 306–324.
3.
AlnajjarF.ZinI. B. M.MuraseK. (2009). A hierarchical autonomous robot controller for learning and memory: Adaptation in a dynamic environment. Adaptive Behavior, 17(3), 179–196.
4.
ArenaP.De FioreS.PataneL.PollinoM.VenturaC. (2009). STDP-based behavior learning on TriBot robot. In Proceedings of the SPIE, International Society for Optical Engineering, WA, USA.
5.
BiG.PooM. (1998). Activity-induced synaptic modifications in hippocampal culture: Dependence on spike timing, synaptic strength and cell type. Journal of Neuroscience, 18, 10464–10472.
6.
BiG.PooM. (2001). Synaptic modification by correlated activity: Hebb’s postulate revisited. Annual Review of Neuroscience24, 139–66.
7.
BohteS. M.MozerM. C. (2007). Reducing de variability of neural responses: A computational theory of spike-timing dependant plasticity. Neural Computation, 19, 371–403.
8.
BohteS. M. (2004). The evidence for neural information processing with precise spike-times: A survey. Natural computing, 3(2), 195–206.
9.
BushD.PhilippidesA.HusbandsP.O’SheaM. (2010). Spike-timing dependent plasticity and the cognitive map. Frontiers in Computational Neuroscience, 4, 142.
10.
CaporaleN.DanY. (2008). Spike timing-dependent plasticity: A Hebbian learning rule. Annual Review of Neuroscience, 31, 25–46.
11.
ChielH. J.BeerR. D. (1997). The brain has a body: Adaptive behavior emerges from interactions of nervous system, body and environment. Trends in Neurosciences, 20, 553–557.
12.
ChristodoulouC.BugmannG.ClarksonT.G. (2002). A spiking neuron model: Applications and learning. Neural Networks, 15, 891–908.
13.
CowanW. M.SüdhofT. C.StevensC. F. (2001). Synapses. Baltimore, MD: Johns Hopkins University Press.
14.
CyrA.BoukadoumM.PoirierP. (2009). AI-SIMCOG: A simulator for spiking neurons and multiple animat’s behaviours. Neural Computation & Application, 18(5), 431–446.
15.
DanY.PooM.-M. (2006). Spike timing-dependant plasticity: From synapse to perception. Physiological Reviews86, 1033–1048.
16.
Di PaoloE. A. (2002). Spike timing dependent plasticity for evolved robots. Adaptive Behavior, 10, 243–263.
17.
FloreanoD.MattiussiC. (2008). Bio-inspired artificial intelligence: Theories, methods and technologies. Cambridge, MA: MIT Press.
18.
FlorianR. V. (2010). The chronotron: A neuron that learns to fire temporally-precise spike pattern. Available from Nature Proceedings, http://hdl.handle.net/10101/npre.2010.5190.3.
GerstnerW.KistlerW. (2002). Spiking neuron models: Single neurons, populations, plasticity. Cambridge: Cambridge University Press.
21.
GjorgjievaJ.ClopathC.AudetJ.PfisterJ.P. (2011). A triplet spike-timing-dependent plasticity model generalizes the Bienenstock–Cooper–Munro rule to higher-order spatiotemporal correlations, Proceedings of the National Academy of Science USA, 108, 19383–19388.
22.
GütigR.AharonovR.RotterS.SompolinskyH. (2003). Learning input correlations through nonlinear temporally asymmetric Hebbian plasticity. The Journal of Neuroscience, 23(9), 3697–3714.
23.
IzhikevichE. M. (2003). Simple model of spiking neurons. IEEE Transactions on Neural Networks, 14, 1569–1572.
24.
IzhikevichE. M. (2007). Solving the distal reward problem through linkage of STDP and dopamine signaling. Cerebral Cortex Advance, 17, 2443–2452.
25.
KempterR.GerstnerW.HemmenJ. L. V. (1999). Hebbian learning and spiking neurons. Physical Review E, 59(4), 4498–4514.
26.
KistlerW. M.van HemmenJ. L. (2000). Modeling synaptic plasticity in conjunction with the timing of pre- and postsynaptic action potentials. Neural Computation, 12, 385–405.
27.
LetzkusJ. J.KampaB. M.StuartG. J. (2007). Does spike-timing-dependant synaptic plasticity underlie memory formation?Proceedings of the Australian Physiological Society38, 15–23.
28.
LieuC.ShapiroJ. (2007). Implementing classical conditioning with spiking neurons. In de SaJ. Marques. (Eds.), ICANN 2007, Part I, LNCS, 4668 (pp. 400–410). Berlin: Springer-Verlag.
29.
MaassW.BishopC. M. (Eds). (1999). Pulsed neural networks. Cambridge, MA: Bradford Book, MIT Press.
30.
MarkramH.LubkeJ.FrotscherM.SakmannB. (1997). Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSEs. Science, 275, 213–215.
31.
MarkramH.GerstnerW.SjöströmP.J. (2011). A history of spike-timing-dependent plasticity. Review article. Frontiers in Synaptic Neuroscience, 3(4), 1–24.
32.
MehrtashN.JungD.HellmitchH. H.SchoenauerT.LuV.KlarH. (2003). Synaptic plasticity in spiking neural networks (sp inn): A system approach. IEEE Transactions on Neural Networks, 14(5), 980–992.
RobertsP. D.LeenT. K. (2010). Anti-Hebbian spike-timing-dependent plasticity and adaptative sensory processing. Frontiers in Computational Neurosciences, 4(156), 1–11.
35.
RobertsP. D.BellC. C. (2002). Spike timing dependent synaptic plasticity in biological systems. Biological Cybernetics, 87, 392–403.
36.
RudyJ. W. (2008). The neurobiology of learning and memory. Sunderland, MA: Sinauer Associates, Inc.
37.
SchmajukN. A. (2010). Mechanisms in classical conditioning. Cambridge: Cambridge University Press.
38.
ShouvalH.Z.KalantzisG. (2005). Stochastic properties of synaptic transmission affect the shape of spike time-dependent plasticity curves. Journal of Neurophysiology, 93, 1069–1073.
39.
ShouvalH.Z.WangS.S.-H.WittenbergG.M. (2010). Spike timing dependent plasticity: A consequence of more fundamental learning rules. Frontiers in Computational Neuroscience, 4, 19.
40.
SjöströmP. J.NelsonS. B. (2002). Spike timing, calcium signals and synaptic plasticity. Current Opinion in Neurobiology, 12, 305–314.
41.
SongS.MillerK. D.AbbottL. F. (2000). Competitive Hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience, 3(9), 919–926.
42.
SoulaH.AlwanA.BeslonG. (2005). Learning at the edge of chaos: Temporal coupling of spiking neurons controller for autonomous robotic. AAAI Spring Symposium on Developmental Robotics, Stanford, CT.
