Spike-based indirect training of a spiking neural network-controlled virtual insect

Spiking neural networks (SNNs) have been shown capable of replicating the spike patterns observed in biological neuronal networks, and of learning via biologically-plausible mechanisms, such as synaptic time-dependent plasticity (STDP). As result, they are commonly used to model cultured neural network, and memristor-based neuromorphic computer chips that aim at replicating the scalability and functionalities of biological circuitries. These examples of SNNs, however, do not allow for the direct manipulation of the synaptic strengths (or weights) as required by existing training algorithms. Therefore, this paper presents an indirect training algorithm that, instead, is designed to manipulate input spike trains (stimuli) that can be implemented by patterns of blue light, or controlled input voltages, to induce the desired synaptic weights changes via STDP. The approach is demonstrated by training an SNN to control a virtual insect that seeks to reach a target location in an obstacle populated environment, without any prior control or navigation knowledge. The simulation results illustrate the feasibility and efficiency of the proposed indirect training algorithm for a biologically-plausible sensorimotor system.

[1]  Nikola Kasabov,et al.  Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. , 2013, Neural networks : the official journal of the International Neural Network Society.

[2]  Jean-Pascal Pfister,et al.  Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning , 2005, Neural Computation.

[3]  C. Nicholson.  Electric current flow in excitable cells J. J. B. Jack, D. Noble &R. W. Tsien Clarendon Press, Oxford (1975). 502 pp., £18.00 , 1976, Neuroscience.

[4]  Deborah Estrin,et al.  Guest Editors' Introduction: Overview of Sensor Networks , 2004, Computer.

[5]  Silvia Ferrari,et al.  Biologically realizable reward-modulated hebbian training for spiking neural networks , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[6]  Pinaki Mazumder,et al.  Memristor based STDP learning network for position detection , 2010, 2010 International Conference on Microelectronics.

[7]  R. Siegel,et al.  Land mine detection , 2002 .

[8]  Wolfgang Maass,et al.  Noisy Spiking Neurons with Temporal Coding have more Computational Power than Sigmoidal Neurons , 1996, NIPS.

[9]  P. Krogsgaard‐Larsen,et al.  The Binding of [3H]AMPA, a Structural Analogue of Glutamic Acid, to Rat Brain Membranes , 1982, Journal of neurochemistry.

[10]  Niru Maheswaranathan,et al.  Emergent bursting and synchrony in computer simulations of neuronal cultures , 2012, Front. Comput. Neurosci..

[11]  Robert A. Legenstein,et al.  What Can a Neuron Learn with Spike-Timing-Dependent Plasticity? , 2005, Neural Computation.

[12]  Harald Burgsteiner,et al.  Imitation learning with spiking neural networks and real-world devices , 2006, Eng. Appl. Artif. Intell..

[13]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[14]  Roland Strauss,et al.  Modeling the insect mushroom bodies: application to a delayed match-to-sample task. , 2013, Neural networks : the official journal of the International Neural Network Society.

[15]  Bernhard Nebel,et al.  CS Freiburg: coordinating robots for successful soccer playing , 2002, IEEE Trans. Robotics Autom..

[16]  Xu Zhang,et al.  A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques , 2012, Adv. Artif. Neural Syst..

[17]  Yong Wang,et al.  Energy-efficient computing for wildlife tracking: design tradeoffs and early experiences with ZebraNet , 2002, ASPLOS X.

[18]  Miguel A. L. Nicolelis,et al.  A simulator for the analysis of neuronal ensemble activity: application to reaching tasks , 2002, Neurocomputing.

[19]  Steven M. LaValle,et al.  Planning algorithms , 2006 .

[20]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[21]  José Carlos Príncipe,et al.  Approximate reconstruction of bandlimited functions for the integrate and fire sampler , 2009, Advances in Computational Mathematics.

[22]  C. Pennartz.  Reinforcement learning by Hebbian synapses with adaptive thresholds , 1997, Neuroscience.

[23]  Silvia Ferrari,et al.  Multiobjective Algebraic Synthesis of Neural Control Systems by Implicit Model Following , 2009, IEEE Transactions on Neural Networks.

[24]  Razvan V. Florian,et al.  Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity , 2007, Neural Computation.

[25]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1952, The Journal of physiology.

[26]  Erik De Schutter,et al.  Computational Modeling Methods for Neuroscientists , 2009 .