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

  title={Spike-based indirect training of a spiking neural network-controlled virtual insect},
  author={Xu Zhang and Ziye Xu and Craig S. Henriquez and Silvia Ferrari},
  journal={52nd IEEE Conference on Decision and Control},
  • Xu Zhang, Ziye Xu, S. Ferrari
  • Published 1 December 2013
  • Computer Science, Biology
  • 52nd IEEE Conference on Decision and Control
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… 
Supervised Learning in SNN via Reward-Modulated Spike-Timing-Dependent Plasticity for a Target Reaching Vehicle
This paper uses the supervised reward-modulated Spike-Timing-Dependent-Plasticity learning rule to train two different SNN-based sub-controllers to replicate a desired obstacle avoiding and goal approaching behavior, provided by pre-generated datasets.
A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks
This paper surveys the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications, and highlights the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities.
Robotic arm controlling based on a spiking neural circuit and synaptic plasticity
Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks
A spatio-temporal backpropagation (STBP) algorithm for training high-performance SNNs is proposed, which combines the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD), and does not require any additional complicated skill.
Experimental Study of Reinforcement Learning in Mobile Robots Through Spiking Architecture of Thalamo-Cortico-Thalamic Circuitry of Mammalian Brain
Experimental studies prove that through the proposed method, thalamo-cortical structure could be trained successfully to learn to perform various robotic tasks.
A Possible Neural Circuit for Decision Making and Its Learning Process
A biologically plausible decision circuit consisting of computational neuron and synapse models and its learning mechanism are designed and used successfully to simulate the behavior of Drosophila exhibited in real experiments.
A decision-making model based on a spiking neural circuit and synaptic plasticity
This model uses synaptic plasticity to explain changes in decision output given the same environment and explains at the micro-level how observable decision-making behavior at the macro-level is acquired and achieved.
Neuron-Like Optical Spiking Generation Based on Silicon Microcavity
It is shown that neuron-like optical spiking can be generated in silicon-based photonic microcavity, and it is proved that the optical pulse have all the typical characteristics of nerve spiking pulse.
A low cost biomimetic implementation of a CPG based on AdEx neuron model
Experimental results show that the proposed CPG has functionality of a locomotion pattern with periodic rhythmic movements, and according to the results and implementation costs, the proposed bio inspired CPG can be used in artificial lamprey design.


A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques
An indirect learning method that induces changes in the synaptic weights by modulating spike-timing-dependent plasticity by means of controlled input spike trains.
Biologically realizable reward-modulated hebbian training for spiking neural networks
A novel algorithm based on reward-modulated spike-timing-dependent plasticity that is biologically plausible and capable of training a spiking neural network to learn the exclusive-or (XOR) computation, through rate-based coding is presented.
What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?
It is demonstrated through extensive computer simulations that the theoretically predicted convergence of STDP with teacher forcing also holds for more realistic models for neurons, dynamic synapses, and more general input distributions.
Imitation learning with spiking neural networks and real-world devices
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity
It is shown that the modulation of STDP by a global reward signal leads to reinforcement learning, and analytically learning rules involving reward-modulated spike-timing-dependent synaptic and intrinsic plasticity are derived, which may be used for training generic artificial spiking neural networks, regardless of the neural model used.
Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition.
Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning
A supervised learning paradigm is used to derive a synaptic update rule that optimizes by gradient ascent the likelihood of postsynaptic firing at one or several desired firing times, and finds that the optimal strategy of up- and downregulating synaptic efficacies depends on the relative timing between presynaptic spike arrival and desired post Synaptic firing.
Reinforcement learning by Hebbian synapses with adaptive thresholds
Emergent bursting and synchrony in computer simulations of neuronal cultures
An in silico network of cortical neurons based on known features of similar in vitro networks is developed and it is shown that a large fraction of the variance in firing rates is captured by the first component for bursting networks.
Memristor based STDP learning network for position detection
This work highlights three basic learning rules - winner-take-all (WTA), spike timing dependent plasticity (STDP), and inhibition of return (IOR) and gives a design example implementing WTA combined with STDP in a position detector.