Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting

  title={Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting},
  author={Filip Ponulak and Andrzej J. Kasinski},
  journal={Neural Computation},
Learning from instructions or demonstrations is a fundamental property of our brain necessary to acquire new knowledge and develop novel skills or behavioral patterns. This type of learning is thought to be involved in most of our daily routines. Although the concept of instruction-based learning has been studied for several decades, the exact neural mechanisms implementing this process remain unrevealed. One of the central questions in this regard is, How do neurons learn to reproduce template… 
Learning Spatiotemporally Encoded Pattern Transformations in Structured Spiking Neural Networks
This work introduces a new supervised learning rule, MultilayerSpiker, that can train spiking networks containing hidden layer neurons to perform transformations between spatiotemporal input and output spike patterns using a fully temporal coding scheme.
Encoding Spike Patterns in Multilayer Spiking Neural Networks
This work introduces a learning rule for spiking networks containing hidden neurons which optimizes the likelihood of generating desired output spiking patterns and shows the proposed learning rule allows for a large number of accurate input-output spike pattern mappings to be learnt.
Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks
This work proposes a new supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy, and highlights a novel encoding strategy that can transform image data into compact spatiotemporal patterns for subsequent network processing.
Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding
This work examines the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code and finds the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision.
Training Spiking Neural Networks for Cognitive Tasks: A Versatile Framework Compatible With Various Temporal Codes
A modified SpikeProp learning algorithm is proposed, which ensures better learning stability for SNNs and provides more diverse network structures and coding schemes, and provides a new framework, in which various neural behaviors can be modeled and the underlying computational mechanisms can be studied.
Relative ordering learning in spiking neural network for pattern recognition
SPAN : spike pattern association neuron for learning spatio-temporal sequences
A spiking neuron that is able to learn associations of arbitrary spike trains in a supervised fashion allowing the processing of spatio-temporal information encoded in the precise timing of spikes is presented.
Learning spatio-temporal spike train encodings with ReSuMe, DelReSuMe, and Reward-modulated Spike-timing Dependent Plasticity in Spiking Neural Networks
This work proposes alternative architecture for ReSuMe dealing with heterogeneous synapses and uses dopamine-inspired STDP in SNNs to demonstrate improvements in mapping spatio-temporal patterns of spike trains with the multi-delay mechanism versus single connection.
Spiking Neural Network Learning Models for Spike Sequence Learning and Data Classification
This paper seeks to exploit the advantages of spiking neural networks for spike sequence learning in order to establish two (2) models; batch and sequential learning models for solving data classification tasks using the least squares approach.
A Cross-Correlated Delay Shift Supervised Learning Method for Spiking Neurons with Application to Interictal Spike Detection in Epilepsy
Results presented show that the CCDS learning method achieves learning accuracy and learning speed comparable with ReSuMe, but improves classification accuracy when compared to both the Spike Pattern Association Neuron (SPAN) learning rule and the Tempotron learning rule.


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.
The tempotron: a neuron that learns spike timing–based decisions
This work proposes a new, biologically plausible supervised synaptic learning rule that enables neurons to efficiently learn a broad range of decision rules, even when information is embedded in the spatiotemporal structure of spike patterns rather than in mean firing rates.
Comparison of supervised learning methods for spike time coding in spiking neural networks
This study is motivated by recent experimental results regarding information coding in biological neural systems, which suggest that precise timing of individual spikes may be essential for efficient computation in the brain.
Reinforcement learning with modulated spike timing dependent synaptic plasticity.
This model offers a novel and biologically plausible implementation of reinforcement learning that is capable of training a neural population to produce a very wide range of possible mappings between synaptic input and spiking output.
Experimental Demonstration of Learning Properties of a New Supervised Learning Method for the Spiking Neural Networks
ReSuMe has the following properties that make it an attractive computational tool for the real-life applications such as modeling, identification and control of non-stationary, nonlinear objects, especially of the biological neural and neuro-muscular systems.
Error-backpropagation in temporally encoded networks of spiking neurons
ReSuMe learning method for Spiking Neural Networks dedicated to neuroprostheses control
ReSuMe is considered a Remote Supervised Method for precise learning of spatiotemporal patterns of spikes in Spiking Neural Networks (SNN) for neuroprostheses control and takes advantage of the spike-based Hebbian processes.
ReSuMe-New Supervised Learning Method for Spiking Neural Networks
T thorough analysis of the ReSuMe method reveals its suitability not only to the task of movement control, but also to other real-life applicatio ns including modeling, identification and control of diverse non-statio nary, nonlinear objects.
A gradient descent rule for spiking neurons emitting multiple spikes
A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback
The resulting learning theory predicts that even difficult credit-assignment problems can be solved in a self-organizing manner through reward-modulated STDP, and provides a possible functional explanation for trial-to-trial variability, which is characteristic for cortical networks of neurons but has no analogue in currently existing artificial computing systems.