We describe a Lagrange-Newton framework for the derivation of learning rules with desirable convergence properties and apply it to the case of principal component analysis (PCA). In this framework, a Newton descent is applied to an extended variable vector which also includes Lagrange multipliers introduced with constraints. The Newton descent guarantees equal convergence speed from all directions, but is also required to produce stable fixed points in the system with the extended state vector. The framework produces "coupled" PCA learning rules which simultaneously estimate an eigenvector and the corresponding eigenvalue in cross-coupled differential equations. We demonstrate the feasibility of this approach for two PCA learning rules, one for the estimation of the principal, the other for the estimate of an arbitrary eigenvector-eigenvalue pair (eigenpair).
翻译:我们描述一个Lagrange-Newton框架,用以得出具有适当趋同特性的学习规则,并将其应用于主要组成部分分析(PCA)的情况。在这个框架中,牛顿的下降适用于一个扩展的可变矢量,其中也包括在限制下引入的Lagrange乘数。牛顿的下降保证了所有方向的趋同速度相等,但也需要在系统中与扩展的州矢量产生稳定的固定点。该框架产生了“混合”的五氯苯甲醚学习规则,该规则同时估计了跨组合差异方程中的分解体和相应的折合值。我们展示了两种五氯苯甲醚学习规则的可行性,一种用于估算本金,另一种用于估算任意的乙源-乙基值对子(egenpair)的估算。