Fast subspace tracking and neural network learning by a novel information criterion
Fast subspace tracking and neural network learning by a novel information criterion
复制标题
DOI：
10.1109/icassp.1998.675485
复制
发表时间：
1998-05
期刊：
影响因子：
--
通讯作者：
Y. Miao;Y. Hua
中科院分区：
文献类型：
--
作者：
Y. Miao;Y. Hua
引入一种新的信息准则（NIC）来搜索两层线性神经网络（NN）的最优权值。当且仅当权重跨越协方差矩阵的（期望的）主子空间时，NIC表现出单个全局最大值。NIC的其他平稳点是（不稳定的）鞍点。提出了一种基于NIC的自适应算法，用于估计和跟踪向量序列的主子空间。NIC算法为两层线性神经网络的最优权值提供了快速的在线学习。通过分析和仿真表明，该算法具有收敛速度快等主要优点。
We introduce a novel information criterion (NIC) for searching for the optimum weights of a two-layer linear neural network (NN). The NIC exhibits a single global maximum attained if and only if the weights span the (desired) principal subspace of a covariance matrix. The other stationary points of the NIC are (unstable) saddle points. We develop an adaptive algorithm based on the NIC for estimating and tracking the principal subspace of a vector sequence. The NIC algorithm provides a fast on-line learning of the optimum weights for the two-layer linear NN. The NIC algorithm has several key advantages such as faster convergence which is illustrated through analysis and simulation.