The technological trends underlying the application of CMOS technology in wireless applications are leading to the integration of the RF analog functions and the digital baseband processing into a single chip. Two key technical requirements for this integration are the capability to fabricate high Q passive components and the need to maintain electrical isolation between analog and digital components in the resulting mixed-signal chip. Some basic arguments that illustrate the technological conflict between these two important demands are presented, focusing on their implications for the structure of the IC substrate. This structure and the characteristics of the device package play important robs in determining the levels of coupled ground noise that will be present in the mixed-signal IC. A simple, high-level model for coupled ground noise is presented and used to illustrate the impact of design alternatives for the package and for the IC substrate.

Experimental results from adaptive learning using an optically controlled neural network are presented. The authors have used example problems in nonlinear system identification and signal prediction, two areas of potential neural network application, to study the capabilities of analog neural hardware. These experiments investigated the effects of a variety of nonidealities typical of analog hardware systems. They show that network using large arrays of nonuniform components can perform analog communications with a much higher degree of accuracy than might be expected given the degree of variation in the network's elements. The effects of other common nonidealities, such as noise, weight quantization, and dynamic range limitations, were also investigated.

The proximity effect, caused by electron-beam backscattering during resist exposure, can be compensated for by appropriate local changes in the incident beam dose, but the optimal correction, found iteratively, requires a prohibitively long time for realistic pattern sizes. A neural network has been used to perform these corrections, resulting in a significant decrease in computation time. The correction was first computed for a small test pattern using an iterative method. This solution was used as a training set for an adaptive, feedforward neural network, using back-propagation learning. After training, the network computed the same correction as the iterative method, but in a much shorter time