A computer-implemented method (100) for training a neural network (60) wherein the neural network (60) is configured to determine an output signal (y) based on an input signal (x), and wherein the training comprises training parameters of a depth-by-depth convolutional layer of the neural network (60) wherein the depth-by-depth convolutional layer is initialized based on values extracted from a predefined probability distribution, wherein a variance of the probability distribution is characterized by a reciprocal of a square root of a number of filters applied at each depth of an input of the depth-by-depth convolutional layer.
用于训练神经网络(60)的计算机实现的方法(100),其中所述神经网络(60)被配置成基于输入信号(x)确定输出信号(y),并且其中训练包括训练所述神经网络(60)的逐深度卷积层的参数,其中所述逐深度卷积层基于从预定义概率分布中提取的值来初始化,其中所述概率分布的方差由在所述逐深度卷积层的输入的每个深度处应用的滤波器数量的平方根的倒数表征。
Method for initializing neural network
用于初始化神经网络的方法
2024-11-22
Patent
Electronic Resource
Chinese
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06V |
British Library Conference Proceedings | 1994
|Initializing snakes [object delineation]
IEEE | 1994
|