tf.contrib.distributions.InverseGammaWithSoftplusAlphaBeta.entropy()

tf.contrib.distributions.InverseGammaWithSoftplusAlphaBeta.entropy(name='entropy')

Shanon entropy in nats.

Additional documentation from InverseGamma:

This is defined to be

entropy = alpha - log(beta) + log(Gamma(alpha))
+ (1-alpha)digamma(alpha)

where digamma(alpha) is the digamma function.

doc_TensorFlow
2016-10-14 12:55:01
Comments
Leave a Comment

Please login to continue.