- Addendum to Section 5.2, "Basics of Matrix Manipulation and Calculus":

List of handy formulas for gradients and Jacobian - Addendum to Section 5.2, "Basics of Matrix Manipulation and Calculus":

Formulas for matrix inversion in block form - Addendum to Section 5.5, "Recursive Least-Squares Estimator":

Incremental formula for LSE error measures - Addendum to Section 5.5, "Recursive Least-Squares Estimator":

Recursive LSE in the number of parameters - Addendum to Section 5.8, "LSE for Nonlinear Models":

List of nonlinear models that can be transformed into linear ones - Addendum to Ch 10.9.2:

Sec10.9.2.ps (PostScript file)

This is Eiji Mizutani's paper at WCCI (World Congress on Computational Intelligence) 1998. The paper points out a connection between reinforce learning and recurrent NNs to solve non-Markovian problems. A simple concrete simulation example is described in the paper. - Addendum to "Policy-only Learning" in Chapter 10:

Sample path-based policy-only learning by actor neural networks - The following two papers are supplementary materials on the trust-region methods on page 139 and Section 6.8:

2,440 page hits since Aug 24, 1998