Activation functions¶

statinf.ml.activations.logit(x, weights, bias=0, tensor=False)[source]¶

Logistic function

Parameters

• x (numpy.array) – Input value

• weights (numpy.array) – Vector of weights \(\beta\)

• bias (numpy.array) – Vector of bias \(\epsilon\), defaults to 0.

• tensor (bool, optional) – Perform computation as tensor (theano type), defaults to False

Returns

Logistic transformation: \(logit(x, \beta) = \dfrac{1}{1 + e^{-x \beta}}\)

Return type

float

statinf.ml.activations.relu(x)[source]¶

Rectified Linear Units activation function

Parameters

x (float or numpy.array) – Input value

Returns

Activated value: \(relu(x) = \max(0, x)\)

Return type

float

statinf.ml.activations.sigmoid(x)[source]¶

Sigmoid activation function

Parameters

x (float or numpy.array) – Input value

Returns

Sigmoid activated value: \(sigmoid(x) = \dfrac{1}{1 + e^{-x}}\)

Return type

float

statinf.ml.activations.softplus(x)[source]¶

Softplus activation function

Parameters

x (float or numpy.array) – Input value

Returns

Activated value: \(softplus(x) = \log(1 + e^{-x})\)

Return type

float

statinf.ml.activations.tanh(x)[source]¶

Hyperbolic tangent activation function

Parameters

x (float or numpy.array) – Input value

Returns

Activated value: \(tanh(x)\)

Return type

float