These neuron types can be used in any place that Nengo neuron types can be used.
nengo_extras.neurons.
SoftLIFRate
(sigma=1.0, **lif_args)[source]¶LIF neuron with smoothing around the firing threshold.
This is a rate version of the LIF neuron whose tuning curve has a continuous first derivative, due to the smoothing around the firing threshold. It can be used as a substitute for LIF neurons in deep networks during training, and then replaced with LIF neurons when running the network [R1313].
Parameters:  sigma : float
amplitude : float
tau_rc : float
tau_ref : float


References
[R1313]  (1, 2) E. Hunsberger & C. Eliasmith (2015). Spiking Deep Networks with LIF Neurons. arXiv Preprint, 1510. https://arxiv.org/abs/1510.08829 
nengo_extras.neurons.
FastLIF
(tau_rc=0.02, tau_ref=0.002, min_voltage=0, amplitude=1)[source]¶Faster version of the leaky integrateandfire (LIF) neuron model.
This neuron model is faster than LIF
but does not produce the ideal
firing rate for larger dt
due to linearization of the tuning curves.
nengo_extras.neurons.
spikes2events
(t, spikes)[source]¶Return an eventbased representation of spikes (i.e. spike times)
nengo_extras.neurons.
rates_isi
(t, spikes, midpoint=False, interp='zero')[source]¶Estimate firing rates from spikes using ISIs.
Parameters:  t : (M,) array_like
spikes : (M, N) array_like
midpoint : bool, optional
interp : string, optional


Returns:  rates : (M, N) array_like

nengo_extras.neurons.
rates_kernel
(t, spikes, kind='gauss', tau=0.04)[source]¶Estimate firing rates from spikes using a kernel.
Parameters:  t : (M,) array_like
spikes : (M, N) array_like
kind : str {‘expon’, ‘gauss’, ‘expogauss’, ‘alpha’}, optional
tau : float

