Kayser Christoph, Körding Konrad P, König Peter
Institute of Neuroinformatics, University / ETH Zürich, Winterthurerstrasse 190, 8057 Zürich, Switzerland.
Neural Comput. 2003 Aug;15(8):1751-9. doi: 10.1162/08997660360675026.
Learning in neural networks is usually applied to parameters related to linear kernels and keeps the nonlinearity of the model fixed. Thus, for successful models, properties and parameters of the nonlinearity have to be specified using a priori knowledge, which often is missing. Here, we investigate adapting the nonlinearity simultaneously with the linear kernel. We use natural visual stimuli for training a simple model of the visual system. Many of the neurons converge to an energy detector matching existing models of complex cells. The overall distribution of the parameter describing the nonlinearity well matches recent physiological results. Controls with randomly shuffled natural stimuli and pink noise demonstrate that the match of simulation and experimental results depends on the higher-order statistical properties of natural stimuli.
神经网络中的学习通常应用于与线性核相关的参数，并保持模型的非线性不变。因此，对于成功的模型，必须使用先验知识来指定非线性的属性和参数，而这种先验知识往往是缺失的。在此，我们研究同时调整非线性和线性核。我们使用自然视觉刺激来训练一个简单的视觉系统模型。许多神经元收敛到一个与现有复杂细胞模型相匹配的能量检测器。描述非线性的参数的整体分布与最近的生理学结果非常匹配。使用随机打乱的自然刺激和粉红噪声进行的对照实验表明，模拟结果与实验结果的匹配取决于自然刺激的高阶统计特性。
