Switched-capacitor Neural Networks Research Articles

Programmable switched-capacitor neural network for MVDR beamforming

In this paper, a real-time adaptive antenna array based on a neural network approach is presented. Since an array operating in a nonstationary environment requires a programmable synaptic weight matrix for the neural network, the switched-capacitor (SC) circuits with the capability of programmability and reconfigurability is conducted to implement the neural-based adaptive array. Moreover, the SC techniques can directly implement the neural network with less chip area and provide the ratio of SC-equivalent resistors with accuracy of 0.1 percent. Programming of the switched-capacitor values could be made by allocating each synaptic weight to a set of parallel capacitors with values in a digitally programmable capacitor array (PCA). A relatively wide range of values (5 to 10 binary bits resolution) can be realized for each synaptic weight. A simulation tool called SWITCAP is used to verify the validity and performance of the proposed implementation. Experimental results show that the computation time of solving a linear array of 5 elements is about 0.1 ns for 1 ns time constant and is independent of signal power levels.

A self-organizing switched-capacitor neural network

A novel analog realization of a self-organizing neural network using switched-capacitors is presented. The design is entirely synchronous and incorporates a 'winner-take-all' circuit, as well as a circuit capable of computing the neural activity required by the dot product operation. A switched-capacitor circuit capable of implementing the basic learning law in self-organizing neural networks is also presented. The entire system, which avoids the cumbersome use of polysilicon resistors in VLSI technology, can easily form the backbone of a neurocomputer devoted to competitive learning systems. Also, the binary nature of the input pattern vectors lends itself to application areas such as pattern recognition and image processing. Design equations are presented and confirmed using HSPICE simulations. Experimental results of a breadboard version of the 'winner-take-all' circuit are also presented and verified, and a chip has been submitted for fabrication.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

A purely capacitive synaptic matrix for fixed-weight neural networks

It is shown that the synaptic function of fixed-weight neural networks can be implemented using only one capacitor. The resulting synaptic matrix, being devoid of active devices, offers very high space-power efficiency and speed along with large synapse capacity with considerable analog depth. The generic capacitor matrix is analyzed on the basis of dendritic charge conservation. The results are used to determine network limitations and to design a double-poly CMOS feedforward classifier that is capable of correcting any 3-b error occurring in a set of thirty 16-b code-patterns. Each synapse occupies 16.5 mu m*10 mu m of field-oxide space for the very conservative 3- mu m rules employed in this particular design. Electrical performance is verified through simulation. Comparison between the proposed network and other switched-capacitor neural network configurations is also included. >

Switched-capacitor neural networks using pulse based arithmetic

A possible VLSI implementation of a neural network using SC networks is presented. The frequency of a presynaptic pulse is used as a measure of its state, Vj(f). Synaptic multiplication is made possible by controlling input voltages to the SC multiplier and clock frequencies, Vj(f). Programmable positive and negative weights are allowed. The design is asynchronous and does not require any master clocks.

Neural net based nonstandard A/D conversion

A technique for nonstandard A/D conversion of signals subject to a fidelity criterion is described, based on Hopfield neural networks. Switched-capacitor neural networks offer a natural means for efficient implementation of the proposed technique. Applications include all forms of PCM coding, oversampled A/D conversion and digital image halftoning.

Switched-capacitor neural networks for linear programming

A circuit for online solving of linear programming problems is presented. The circuit uses switched-capacitor techniques and is thus suitable for monolithic implementation. The connection of the proposed circuit to analogue neural networks is also outlined. >

Switched-capacitor neural networks

A neural network implementation is proposed, consisting of switches, capacitors and inverters. A number of potentially attractive features of the implementation are pointed out.