chainer.distributions.Normal¶

class chainer.distributions.Normal(loc, scale=None, **kwargs)[source]¶

Normal Distribution.

The probability density function of the distribution is expressed as

\[p(x;\mu,\sigma) = \frac{1}{\sqrt{2\pi\sigma^2}} \exp\left(-\frac{(x-\mu)^2}{2\sigma^2}\right)\]

Parameters

loc (Variable or N-dimensional array) – Parameter of distribution representing the location \(\mu\). This is the mean parameter.
scale (Variable or N-dimensional array) – Parameter of distribution representing the scale \(\sigma\). Either scale or log_scale (not both) must have a value.
log_scale (Variable or N-dimensional array) – Parameter of distribution representing the scale \(\log(\sigma)\). Either scale or log_scale (not both) must have a value.

Methods

cdf(x)[source]¶

Evaluates the cumulative distribution function at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Cumulative distribution function value evaluated at x.
Return type: Variable

icdf(x)[source]¶

Evaluates the inverse cumulative distribution function at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Inverse cumulative distribution function value evaluated at x.
Return type: Variable

log_cdf(x)[source]¶

Evaluates the log of cumulative distribution function at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Logarithm of cumulative distribution function value evaluated at x.
Return type: Variable

log_prob(x)[source]¶

Evaluates the logarithm of probability at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Logarithm of probability evaluated at x.
Return type: Variable

log_survival_function(x)[source]¶

Evaluates the logarithm of survival function at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Logarithm of survival function value evaluated at x.
Return type: Variable

perplexity(x)[source]¶

Evaluates the perplexity function at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Perplexity function value evaluated at x.
Return type: Variable

prob(x)[source]¶

Evaluates probability at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Probability evaluated at x.
Return type: Variable

sample(sample_shape=())[source]¶

Samples random points from the distribution.

This function calls sample_n and reshapes a result of sample_n to sample_shape + batch_shape + event_shape. On implementing sampling code in an inherited ditribution class, it is not recommended to override this function. Instead of doing this, it is preferable to override sample_n.

Parameters: sample_shape (tuple of int) – Sampling shape.
Returns: Sampled random points.
Return type: Variable

sample_n(n)[source]¶

Samples n random points from the distribution.

This function returns sampled points whose shape is (n,) + batch_shape + event_shape. When implementing sampling code in a subclass, it is recommended to override this method.

Parameters: n (int) – Sampling size.
Returns: sampled random points.
Return type: Variable

survival_function(x)[source]¶

Evaluates the survival function at the given points.

Parameters: x (Variable or N-dimensional array) – Data points in the domain of the distribution
Returns: Survival function value evaluated at x.
Return type: Variable

Attributes

batch_shape¶

Returns the shape of a batch.

Returns: The shape of a sample that is not identical and independent.
Return type: tuple

covariance¶

Returns the covariance of the distribution.

Returns: The covariance of the distribution.
Return type: Variable

entropy¶

event_shape¶

Returns the shape of an event.

Returns: The shape of a sample that is not identical and independent.
Return type: tuple

loc¶

log_scale¶

mean¶

mode¶

Returns the mode of the distribution.

Returns: The mode of the distribution.
Return type: Variable

params¶

Returns the parameters of the distribution.

Returns: The parameters of the distribution.
Return type: dict

scale¶

stddev¶

support¶

Returns the support of the distribution.

Returns: String that means support of this distribution.
Return type: str

variance¶

xp¶

Array module for the distribution.

Depending on which of CPU/GPU this distribution is on, this property returns numpy or cupy.