by Charlotte Le Mouel, Kenneth D. Harris, Pierre Yger
Abstract:
Learning to categorise sensory inputs by generalising from a few examples whose category is precisely known is a crucial step for the brain to produce appropriate behavioural responses. At the neuronal level, this may be performed by adaptation of synaptic weights under the influence of a training signal, in order to group spiking patterns impinging on the neuron. Here we describe a framework that allows spiking neurons to perform such “supervised learning”, using principles similar to the Support Vector Machine, a well-established and robust classifier. Using a hinge-loss error function, we show that requesting a margin similar to that of the SVM improves performance on linearly non-separable problems. Moreover, we show that using pools of neurons to discriminate categories can also increase the performance by sharing the load among neurons.
Reference:
Charlotte Le Mouel, Kenneth D. Harris, Pierre Yger, 2014. Supervised learning with decision margins in pools of spiking neurons, Journal of computational neuroscience, volume 37.
Bibtex Entry:
@article{LeMouel2014, abstract = {Learning to categorise sensory inputs by generalising from a few examples whose category is precisely known is a crucial step for the brain to produce appropriate behavioural responses. At the neuronal level, this may be performed by adaptation of synaptic weights under the influence of a training signal, in order to group spiking patterns impinging on the neuron. Here we describe a framework that allows spiking neurons to perform such "supervised learning", using principles similar to the Support Vector Machine, a well-established and robust classifier. Using a hinge-loss error function, we show that requesting a margin similar to that of the SVM improves performance on linearly non-separable problems. Moreover, we show that using pools of neurons to discriminate categories can also increase the performance by sharing the load among neurons.}, author = {Le Mouel, Charlotte and Harris, Kenneth D. and Yger, Pierre}, day = {28}, doi = {10.1007/s10827-014-0505-9}, issn = {1573-6873}, journal = {Journal of computational neuroscience}, keyword = {Synapses}, language = {eng}, month = {Oct}, number = {2}, pages = {333--344}, title = {Supervised learning with decision margins in pools of spiking neurons.}, url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4159595/pdf/10827_2014_Article_505.pdf}, volume = {37}, year = {2014} }