Enum: ActivationFunctionType

Common activation functions used in neural networks (Clause 3.4.1).

URI: iso22989:ActivationFunctionType

Permissible Values

Value	Meaning	Description
sigmoid	None	Logistic sigmoid activation
tanh	None	Hyperbolic tangent activation
relu	None	Rectified linear unit activation
leaky_relu	None	Rectified linear unit with non-zero gradient below zero
softmax	None	Softmax activation producing a probability distribution
linear	None	Identity / linear activation
other	None	Activation function not enumerated explicitly

Slots

Name	Description
activation_function	Predominant activation function used in the network (Clause 3

In Subsets

• Terminology

Identifier and Mapping Information

Schema Source

• from schema: https://w3id.org/lmodel/iso22989

LinkML Source

name: ActivationFunctionType
description: Common activation functions used in neural networks (Clause 3.4.1).
in_subset:
- terminology
from_schema: https://w3id.org/lmodel/iso22989
rank: 1000
permissible_values:
  sigmoid:
    text: sigmoid
    description: Logistic sigmoid activation.
  tanh:
    text: tanh
    description: Hyperbolic tangent activation.
  relu:
    text: relu
    description: Rectified linear unit activation.
  leaky_relu:
    text: leaky_relu
    description: Rectified linear unit with non-zero gradient below zero.
  softmax:
    text: softmax
    description: Softmax activation producing a probability distribution.
  linear:
    text: linear
    description: Identity / linear activation.
  other:
    text: other
    description: Activation function not enumerated explicitly.