Logistic Sigmoid

Compute the logistic sigmoid $\sigma (x)=1\mathrm{/}(1+e^{-x})\backslash sigma(x)=1/(1+e^\{-x\})$ for an array of real logits without overflow for large positive or negative inputs.

Implement solve(x).

Returns. Return a float NumPy array of the same shape with values in $[0,1][0,\; 1]$.

Examples

Example 1

Input:

solve([0.0])

Output:

[0.5]

Example 2

Input:

solve([2.0, -2.0])

Output:

[0.880797, 0.119203]

Example 3

Input:

solve([1000.0, -1000.0])

Output:

[1.0, 0.0]