Parabolic bursting in an excitable system coupled with a slow oscillation
SIAM Journal on Applied Mathematics
A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
Open questions about computation in cerebral cortex
Parallel distributed processing: explorations in the microstructure of cognition, vol. 2
Competitive learning: from interactive activation to adaptive resonance
Connectionist models and their implications: readings from cognitive science
Analysis of neural excitability and oscillations
Methods in neuronal modeling
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Reduction of conductance-based neuron models
Biological Cybernetics
An adaptive conjugate gradient learning algorithm for efficient training of neural networks
Applied Mathematics and Computation
Machine learning: neural networks, genetic algorithms, and fuzzy systems
Machine learning: neural networks, genetic algorithms, and fuzzy systems
Neural network fundamentals with graphs, algorithms, and applications
Neural network fundamentals with graphs, algorithms, and applications
Fast sigmoidal networks via spiking neurons
Neural Computation
Weakly connected neural networks
Weakly connected neural networks
A gradient descent rule for spiking neurons emitting multiple spikes
Information Processing Letters - Special issue on applications of spiking neural networks
Type i membranes, phase resetting curves, and synchrony
Neural Computation
Lower bounds for the computational power of networks of spiking neurons
Neural Computation
Autonomous biped gait pattern based on Fuzzy-CMAC neural networks
Integrated Computer-Aided Engineering
Improved spiking neural networks for EEG classification and epilepsy and seizure detection
Integrated Computer-Aided Engineering
Enhanced probabilistic neural network with local decision circles: A robust classifier
Integrated Computer-Aided Engineering
Computers in Biology and Medicine
Computer theory and digital image processing applied to brain activation recognition
Integrated Computer-Aided Engineering
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Expert Systems with Applications: An International Journal
A fuzzy logic system for seizure onset detection in intracranial EEG
Computational Intelligence and Neuroscience
WCCI'12 Proceedings of the 2012 World Congress conference on Advances in Computational Intelligence
A modified one-layer spiking neural network involves derivative of the state function at firing time
ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I
A Modified Spiking Neuron that Involves Derivative of the State Function at Firing Time
Neural Processing Letters
Supervised learning in multilayer spiking neural networks
Neural Computation
Automated EEG analysis of epilepsy: A review
Knowledge-Based Systems
A new supervised learning algorithm for spiking neurons
Neural Computation
| Hi-index | 0.01 |
A new Multi-Spiking Neural Network (MuSpiNN) model is presented in which information from one neuron is transmitted to the next in the form of multiple spikes via multiple synapses. A new supervised learning algorithm, dubbed Multi-SpikeProp, is developed for training MuSpiNN. The model and learning algorithm employ the heuristic rules and optimum parameter values presented by the authors in a recent paper that improved the efficiency of the original single-spiking Spiking Neural Network (SNN) model by two orders of magnitude. The classification accuracies of MuSpiNN and Multi-SpikeProp are evaluated using three increasingly more complicated problems: the XOR problem, the Fisher iris classification problem, and the epilepsy and seizure detection (EEG classification) problem. It is observed that MuSpiNN learns the XOR problem in twice the number of epochs compared with the single-spiking SNN model but requires only one-fourth the number of synapses. For the iris and EEG classification problems, a modular architecture is employed to reduce each 3-class classification problem to three 2-class classification problems and improve the classification accuracy. For the complicated EEG classification problem a classification accuracy in the range of 90.7%-94.8% was achieved, which is significantly higher than the 82% classification accuracy obtained using the single-spiking SNN with SpikeProp.