XavierUniform

Contents

XavierUniform#

class braintools.init.XavierUniform(scale=1.0, unit=None)#

Xavier/Glorot uniform initialization.

Samples from a uniform distribution with bounds computed to maintain variance across layers. Recommended for tanh and sigmoid activations.

Reference: Glorot & Bengio, “Understanding the difficulty of training deep feedforward neural networks”, AISTATS 2010.

Parameters:

scale (Array | ndarray | bool | number | bool | int | float | complex | Quantity) – Scaling factor (default: 1.0).

Examples

>>> import numpy as np
>>> from braintools.init import XavierUniform
>>>
>>> init = XavierUniform()
>>> rng = np.random.default_rng(0)
>>> weights = init((100, 50), rng=rng)
Contents