A spiking neural network architecture for nonlinear function approximation

Neural Networks

Volumn 14, Issue 6-7, 2001, Pages 933-939

  Iannella, Nicolangelo ^a   Back, Andrew D ^a  

^a RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

Author keywords

Delays; Integrate and fire units; Neural architecture; Nonlinear function approximation; Spiking neurons

Indexed keywords

APPROXIMATION THEORY; SIGNAL ENCODING;

NONLINEAR FUNCTION APPROXIMATIONS;

MULTILAYER NEURAL NETWORKS;

ACCURACY; ARTICLE; CELL FUNCTION; COMPARATIVE STUDY; CYTOARCHITECTURE; ENVIRONMENT; MATHEMATICAL MODEL; METHODOLOGY; NERVE CELL; NERVE CELL NETWORK; NOISE; NONLINEAR SYSTEM; PRIORITY JOURNAL; SIGNAL TRANSDUCTION; SPIKE; SPIKE WAVE; STIMULUS RESPONSE;

ACTION POTENTIALS; ANIMALS; CENTRAL NERVOUS SYSTEM; HUMANS; NERVE NET; NEURAL NETWORKS (COMPUTER); NEURONS; NONLINEAR DYNAMICS; SYNAPTIC TRANSMISSION;

EID: 0034767488     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(01)00080-6     Document Type: Article

References (10)

1. Reading a neural code
2. Approximation by superpositions of a sigmoidal function
3. Reliability and statistical efficiency of a blowfly movement-sensitive neuron
4. Optimization principles for the neural code
5. On the approximate realization of continuous mappings by neural networks
6. Multilayer feedforward networks are universal approximators
7. Fast sigmoidal networks via spiking neurons
8. Computing functions with spiking neurons in temporal coding
9. Probability density methods for smooth function approximation and learning in populations of tuned spiking neurons