We investigate the Fisher information matrix (FIM) of one hidden layer networks with the ReLU activation function and obtain an approximate spectral decomposition of FIM under certain conditions. From this decomposition, we can approximate the main eigenvalues and eigenvectors. We confirmed by numerical simulation that the obtained decomposition is approximately correct when the number of hidden nodes is about 10000.
翻译:我们调查了一个带有雷射线U激活功能的隐蔽层网络的渔业信息矩阵(FIM),并在某些条件下获得FIM的近似光谱分解。从这种分解中,我们可以接近主要的源值和源源体。我们通过数字模拟确认,当隐藏节点的数量约为10000时,获得的分解大致正确。