chore: remove obsolete documentation files for tether modules

Author: Khushiyant

docs/modules.rst

@@ -32,7 +32,7 @@ def rate_encoding(x: torch.Tensor, n_steps: int, gain: float = 1.0) -> torch.Ten
     Returns
     -------
     torch.Tensor
-        Spike tensor with shape (n_steps, *x.shape).
+        Spike tensor with shape (n_steps, \*x.shape).
     """
     shape = (n_steps,) + x.shape
     prob = torch.clamp(x * gain, 0.0, 1.0)
@@ -62,7 +62,7 @@ def latency_encoding(x: torch.Tensor, n_steps: int, tau: float = 1.0, threshold:
     Returns
     -------
     torch.Tensor
-        Spike tensor with shape (n_steps, *x.shape).
+        Spike tensor with shape (n_steps, \*x.shape).
     """
     # Calculate fire time: t_f = tau * ln(x / (x - theta)) ? 
     # Or simplified: t_f = (1 - x) * n_steps

docs/tether.functional.rst

@@ -32,10 +32,11 @@ def get_id(self):
         raise NotImplementedError
 
 class Arctan(Surrogate):
-    """
+    r"""
     Arctan surrogate gradient.
 
     The surrogate derivative is given by:
+
     .. math::
         f'(x) = \\frac{1}{1 + (\\alpha \\pi x)^2}
 
@@ -45,10 +46,11 @@ def get_id(self):
         return 0
 
 class Sigmoid(Surrogate):
-    """
+    r"""
     Sigmoid surrogate gradient.
 
     The surrogate function is a sigmoid, and its derivative is:
+
     .. math::
         f'(x) = \\alpha \\cdot \\sigma(\\alpha x) \\cdot (1 - \\sigma(\\alpha x))
 
@@ -58,10 +60,11 @@ def get_id(self):
         return 1
 
 class FastSigmoid(Surrogate):
-    """
+    r"""
     Fast Sigmoid (approximated) surrogate gradient.
     
     Uses a computationally cheaper approximation of the sigmoid derivative:
+
     .. math::
         f'(x) = \\frac{1}{(1 + |\\alpha x|)^2}