randn
fun <T : DType> randn(shape: Shape, mean: Float = 0.0f, std: Float = 1.0f, dtype: T, random: Random = Random.Default): TensorData<T, *>(source)
Creates a tensor filled with random values from normal distribution.
Return
TensorData filled with normal distributed random values
Parameters
T
the data type constraint extending DType
shape
the shape of the tensor to create
mean
the mean of the normal distribution
std
the standard deviation of the normal distribution
dtype
the data type instance
random
the random number generator (optional, uses default if not provided)