A Tunable Gaussian/Square Function Computation Circuit for Analog Neural Networks
نویسندگان
چکیده
A Gaussian/square function computation circuit suitable for analog neural networks is proposed. It can realize Gaussian and square functions when operating in weak and strong inversion region, respectively. It is shown that the center, width, and peak amplitude of the dc transfer curve can be controlled separably. Measurement results on 3m CMOS fabricated chips confirm theoretical and simulation findings.
منابع مشابه
A New Analog-based LO Harmonic Rejection Technique with Tunable Notch Frequency
An effective technique for mixer LO harmonic rejection in a SAW-less wideband receiver front-end is proposed. The proposed technique provides a tunable notch that can be placed at any frequency like mixer LO harmonics, to avoid the aliasing in baseband after mixing. An analog LC notch is used in a cascode transconductor, and it can reject one of the 3rd or 5th harmonics. T...
متن کاملImplementation of a programmable neuron in CNTFET technology for low-power neural networks
Circuit-level implementation of a novel neuron has been discussed in this article. A low-power Activation Function (AF) circuit is introduced in this paper, which is then combined with a highly linear synapse circuit to form the neuron architecture. Designed in Carbon Nanotube Field-Effect Transistor (CNTFET) technology, the proposed structure consumes low power, which makes it suitable for the...
متن کاملNovel Radial Basis Function Neural Networks based on Probabilistic Evolutionary and Gaussian Mixture Model for Satellites Optimum Selection
In this study, two novel learning algorithms have been applied on Radial Basis Function Neural Network (RBFNN) to approximate the functions with high non-linear order. The Probabilistic Evolutionary (PE) and Gaussian Mixture Model (GMM) techniques are proposed to significantly minimize the error functions. The main idea is concerning the various strategies to optimize the procedure of Gradient ...
متن کاملVLSI design for analog neural computation
information into the cell body, and transmit the output electrical signals through the axon. The paper describes a VLSI design methodology for the implementation of analog artificial neural networks. Analog VLSI circuit techniques offers area-efficient implementation of the functions required in a neural network such as multiplication, summation and Sigmoid transfer function. However, the analo...
متن کاملImplementing radial basis functions using bump-resistor networks - Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International
Radial Basis Function (RBF) networks provide a powerful learning architecture for neural networks [6]. We have implemented a RBF network in analog VLSI using the concept of bump-resistors. A bump-resistor is a nonlinear resistor whose conductance is a Gaussian-like function of the difference of two other voltages. The width of the Gaussian basis functions may be continuously varied so that the ...
متن کامل