From 45e96795e9328f7119c4a760ecb5cdeb5c738f5a Mon Sep 17 00:00:00 2001
From: "Dr. Alexander Henkes" <62153181+ahenkes1@users.noreply.github.com>
Date: Sun, 24 Sep 2023 09:25:07 +0200
Subject: [PATCH] Update snntorch.surrogate.rst

The default surrogate gradient is now ATan instead of Heaviside. This was updated in the tutorials, but not in the docs for surrogate.
---
 docs/snntorch.surrogate.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/snntorch.surrogate.rst b/docs/snntorch.surrogate.rst
index 10a5820d..c404dbdb 100644
--- a/docs/snntorch.surrogate.rst
+++ b/docs/snntorch.surrogate.rst
@@ -3,7 +3,7 @@ snntorch.surrogate
 
 By default, PyTorch's autodifferentiation tools are unable to calculate the analytical derivative of the spiking neuron graph. 
 The discrete nature of spikes makes it difficult for ``torch.autograd`` to calculate a gradient that facilitates learning.
-:mod:`snntorch` overrides the default gradient by using :mod:`snntorch.LIF.Heaviside`.
+:mod:`snntorch` overrides the default gradient by using :mod:`snntorch.surrogate.ATan`.
 
 Alternative gradients are also available in the :mod:`snntorch.surrogate` module. 
 These represent either approximations of the backward pass or probabilistic models of firing as a function of the membrane potential.
@@ -29,7 +29,7 @@ How to use surrogate
 ^^^^^^^^^^^^^^^^^^^^^^^^
 
 The surrogate gradient must be passed as the ``spike_grad`` argument to the neuron model. 
-If ``spike_grad`` is left unspecified, it defaults to :mod:`snntorch.neurons.Heaviside`.
+If ``spike_grad`` is left unspecified, it defaults to :mod:`snntorch.surrogate.ATan`.
 In the following example, we apply the fast sigmoid surrogate to :mod:`snntorch.Synaptic`.
 
 Example::