Title :
Spiking perceptrons
Author :
Rowcliffe, P. ; Jianfeng Feng ; Buxton, H.
Author_Institution :
Dept. of Informatics, Univ. of Sussex, Brighton
fDate :
5/1/2006 12:00:00 AM
Abstract :
A more plausible biological version of the traditional perceptron is presented here with a learning rule which enables training of the neuron on nonlinear tasks. Three different models are introduced with varying inhibitory and excitatory synaptic connections. Using the derived learning rule, a single neuron is trained to successfully classify the XOR problem
Keywords :
brain models; learning (artificial intelligence); XOR problem; biological version; excitatory synaptic connection; learning rule; nonlinear tasks; spiking perceptrons; varying inhibitory synaptic connection; Artificial neural networks; Biological information theory; Biological system modeling; Biology computing; Biomembranes; Brain modeling; Encoding; Multilayer perceptrons; Neurons; Neurophysiology; Integrate-and-fire (IF); learning; perceptrons; spiking networks; xor; Action Potentials; Algorithms; Animals; Artificial Intelligence; Biomimetics; Computer Simulation; Humans; Models, Neurological; Nerve Net; Neural Networks (Computer); Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2006.873274
