Titlebook: Neural Networks and Analog Computation; Beyond the Turing Li Hava T. Siegelmann Book 1999 Birkh?user Boston 1999 Natur.Theorie.complexity.c

范例

裁決

Networks with Rational Weights,et of rationals. In contrast to the case described in the previous chapter, where we dealt only with integer weights, and each neuron could assume two values only, here a neuron can take on countably infinite different values. The analysis of networks with rational weights is a prerequisite for the

溫和女人

Networks with Real Weights,l practical purposes, useless since systems with infinitely precise constants cannot be built. However, the real weights are appealing for the . modeling of analog computation that occurs in nature, as discussed in Chapter 2. In nature, the fact that the constants are not known to us, or cannot even

表主動(dòng)

certain

啜泣

爵士樂

縫紉

Notorious

The Model,In this chapter we introduce the formal model of the neural network to be utilized and analyzed in this book.

defibrillator

Generalized Processor Networks,Up to this point we have analyzed in detail the computational properties of the analog recurrent neural network. From here on we turn to consider more general models of analog computation, and place our network within this wider framework.