Reword documentation summary

jon-tow · Shashi456 · jon-tow · commit 7993ba072e2d · 2019-06-21T03:20:36.000-04:00
Co-Authored-By: Pawan Sasanka Ammanamanchi &lt;Shashi456@users.noreply.github.com&gt;
diff --git a/Sources/TensorFlow/Operators/Math.swift b/Sources/TensorFlow/Operators/Math.swift
@@ -1051,7 +1051,7 @@ func _vjpRelu<T: TensorFlowFloatingPoint>(
     (relu(x), { v in Tensor(x .> 0) * v })
 }
 
-/// Returns the Gaussian Error Linear Unit (GELU) of the specified tensor element-wise.
+/// Returns a tensor by applying the Gaussian Error Linear Unit (GELU) to the specified tensor element-wise.
 ///
 /// Specifically, `gelu` approximates `xP(X <= x)`, where `P(X <= x)` is the Standard Gaussian
 /// cumulative distribution, by computing: x * [0.5 * (1 + tanh[√(2/π) * (x + 0.044715 * x^3)])].

Original file line number	Diff line number	Diff line change
`@@ -1051,7 +1051,7 @@ func _vjpRelu<T: TensorFlowFloatingPoint>(`
`1051`	`1051`	`(relu(x), { v in Tensor(x .> 0) * v })`
`1052`	`1052`	`}`
`1053`	`1053`
`1054`		`-/// Returns the Gaussian Error Linear Unit (GELU) of the specified tensor element-wise.`
	`1054`	`+/// Returns a tensor by applying the Gaussian Error Linear Unit (GELU) to the specified tensor element-wise.`
`1055`	`1055`	`///`
`1056`	`1056`	/// Specifically, `gelu` approximates `xP(X <= x)`, where `P(X <= x)` is the Standard Gaussian
`1057`	`1057`	`/// cumulative distribution, by computing: x * [0.5 * (1 + tanh[√(2/π) * (x + 0.044715 * x^3)])].`