Reading Assignment 5:

1. Chapter 2 of Nils J. Nilsson, The Mathematical Foundations of Learning Machines, Morgan-Kaufmann, San Mateo, CA 1990, pp. 15–42.
2. Eric B. Baum, ``On the capabilities of multilayer perceptrons,'' Journal of Complexity, 4 (1988), pp. 193–215. (The last sentence on the bottom of page 212 should read ``Taking $\gamma = 2$ we see $\delta = \frac{1}{3}$ satisfies Eq.~(A2); i.e., taking $k = \sqrt{N}$, which is the case of interest, we see, as advertised, that almost every set of $N$ randomly ...'')
3. G. Cybenko, ``Approximation by superpositions of a sigmoidal function,'' Math. Control Signals Systems , 2 (1989), pp. 303–314.