Added Scaled Exponential Linear Unit Activation Function #9027
Conversation
for more information, see https://pre-commit.ci
for more information, see https://pre-commit.ci
|
@tianyizheng02 Thanks for your reply in the discussion section!. All checks passed now. |
|
|
||
|
|
||
| def scaled_exponential_linear_unit( | ||
| vector: np.ndarray, alpha: float = 1.6732, _lambda: float = 1.0507 |
There was a problem hiding this comment.
Is there a reason why _lambda has an underscore? Is the user not meant to change this coefficient?
There was a problem hiding this comment.
Yes, firstly lambda is a reserved keyword in python. Secondly both alpha and lambda are fixed constants.
There was a problem hiding this comment.
The user can change these values, that may yield slightly different behaviour from the function, but the default values given to them are alpha: float = 1.6732, _lambda: float = 1.0507.
There was a problem hiding this comment.
Yes, firstly lambda is a reserved keyword in python.
Oh yeah, duh 🤦
Could you rename the variable to something like lambda_ instead? Having an underscore at the start of a variable name generally signifies that the user isn't supposed to use it.
There was a problem hiding this comment.
Ah. Yes for sure, I'll get it done right away!
…ms#9027) * Added Scaled Exponential Linear Unit Activation Function * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update scaled_exponential_linear_unit.py * Update scaled_exponential_linear_unit.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update scaled_exponential_linear_unit.py * Update scaled_exponential_linear_unit.py * Update scaled_exponential_linear_unit.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update scaled_exponential_linear_unit.py * Update scaled_exponential_linear_unit.py --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Added Scaled Exponential Linear Unit Activation (SELU) Function under TheAlgorithms/Python/neural_network/activation_functions. Description of SELU taken from reference link provided in the top comment section in scaled_exponential_linear_unit.py
Fixes #9010
Checklist: