float64

Return a double-precision floating-point number with the magnitude of x and the sign of x*y.

Return a double-precision floating-point number with the magnitude of x and the sign of y.

Return an unsigned 32-bit integer corresponding to the less significant 32 bits of a double-precision floating-point number.

Convert a double-precision floating-point number to a Node-API value.

Research project analyzing stability and robustness of deep learning optimizers (SGD, Adam, SAM) under label noise and precision constraints.

Evaluate the identity function for a double-precision floating-point number.

Convert a double-precision floating-point number to the nearest half-precision floating-point number.

Compute the sum of the absolute values of the real and imaginary components of a double-precision complex floating-point number.

Return an unsigned 32-bit integer corresponding to the more significant 32 bits of a double-precision floating-point number.

Evaluate the identity function for a double-precision floating-point number.

Return an integer corresponding to the unbiased exponent of a double-precision floating-point number.

Return a boolean indicating if the sign bit for a double-precision floating-point number is on (true) or off (false).

Compute the variance of a one-dimensional double-precision floating-point ndarray.

Divide elements of a one-dimensional double-precision floating-point ndarray by the corresponding elements of a second one-dimensional double-precision floating-point ndarray and assign the results to the second ndarray.

Compute the standard deviation of a one-dimensional double-precision floating-point ndarray using a two-pass algorithm.

Compute the variance of a one-dimensional double-precision floating-point ndarray using a one-pass textbook algorithm.

Evaluate the identity function for a double-precision floating-point number.

Compute the variance of a one-dimensional double-precision floating-point ndarray using a one-pass trial mean algorithm.

Compute the variance of a one-dimensional double-precision floating-point ndarray using Welford's algorithm.

Compute the squared hinge loss gradient with respect to a model parameter.