The Scaled Exponential Linear Unit (SELU) is a self-normalizing activation function. When used with proper weight initialization (LeCun normal), SELU automatically maintains zero mean and unit variance activations across layers, eliminating the need for batch normalization.
Given a list of values, apply the SELU activation to each element using the fixed constants lambda and alpha.
The constants are derived analytically to preserve self-normalizing properties:
λ≈1.0507
α≈1.6733
Input: x = [1, -1, 0]
Output: [1.0507, -1.1113, 0.0]
Explanation: Positive values use lambda scaling, while nonpositive values use the scaled exponential branch.
Input: x = [0.5, 1.5, 2.5]
Output: [0.5254, 1.5761, 2.6268]
Store the fixed lambda and alpha constants inside the function.
Round each transformed value to four decimal places before appending it.
Accepts: array
The Scaled Exponential Linear Unit (SELU) is a self-normalizing activation function. When used with proper weight initialization (LeCun normal), SELU automatically maintains zero mean and unit variance activations across layers, eliminating the need for batch normalization.
Given a list of values, apply the SELU activation to each element using the fixed constants lambda and alpha.
The constants are derived analytically to preserve self-normalizing properties:
λ≈1.0507
α≈1.6733
Input: x = [1, -1, 0]
Output: [1.0507, -1.1113, 0.0]
Explanation: Positive values use lambda scaling, while nonpositive values use the scaled exponential branch.
Input: x = [0.5, 1.5, 2.5]
Output: [0.5254, 1.5761, 2.6268]
Store the fixed lambda and alpha constants inside the function.
Round each transformed value to four decimal places before appending it.
Accepts: array