glm_families {tfprobability} | R Documentation |
GLM families
Description
A list of models that can be used as the model
argument in glm_fit()
:
Details
-
Bernoulli
:Bernoulli(probs=mean)
wheremean = sigmoid(matmul(X, weights))
-
BernoulliNormalCDF
:Bernoulli(probs=mean)
wheremean = Normal(0, 1).cdf(matmul(X, weights))
-
GammaExp
:Gamma(concentration=1, rate=1 / mean)
wheremean = exp(matmul(X, weights))
-
GammaSoftplus
:Gamma(concentration=1, rate=1 / mean)
wheremean = softplus(matmul(X, weights))
-
LogNormal
:LogNormal(loc=log(mean) - log(2) / 2, scale=sqrt(log(2)))
wheremean = exp(matmul(X, weights))
. -
LogNormalSoftplus
:LogNormal(loc=log(mean) - log(2) / 2, scale=sqrt(log(2)))
wheremean = softplus(matmul(X, weights))
-
Normal
:Normal(loc=mean, scale=1)
wheremean = matmul(X, weights)
. -
NormalReciprocal
:Normal(loc=mean, scale=1)
wheremean = 1 / matmul(X, weights)
-
Poisson
:Poisson(rate=mean)
wheremean = exp(matmul(X, weights))
. -
PoissonSoftplus
:Poisson(rate=mean)
wheremean = softplus(matmul(X, weights))
.
Value
list of models that can be used as the model
argument in glm_fit()
See Also
Other glm_fit:
glm_fit.tensorflow.tensor()
,
glm_fit_one_step.tensorflow.tensor()