Connectionists: Gradient Descent for Spiking Neural Networks
Terry Sejnowski
terry at salk.edu
Fri Jun 16 19:35:41 EDT 2017
Spiking network models are not differentiable because of discontinuities
at the spike times. This has prevented learning in spiking networks by
gradient descent.
We have a way to overcome this problem and show that it is possible
to train spiking recurrent networks to solve temporal sequence problems
over a wide range of time scales using backpropagation through time:
https://arxiv.org/abs/1706.04698
This can be applied to any spiking neuron model including the Hodgkin-Huxley
model, leaky integrate and fire neurons, the Morris-Lecar model and the
FitzHugh-Nagumo model.
Terry
-----
More information about the Connectionists
mailing list