Direct and indirect classification of high-frequency LNA performance using machine learning techniques

The task of determining low noise amplifier (LNA) high-frequency performance in functional testing is as challenging as designing the circuit itself due to the difficulties associated with bringing high frequency signals off-chip. One possible strategy for circumventing these difficulties is to attempt to predict the high frequency performance measures using measurements taken at lower, more accessible, frequencies. This paper investigates the effectiveness of machine learning based classification techniques at predicting the gain of the amplifier, a key performance parameter, using such an approach. An indirect artificial neural network (ANN) and direct support vector machine (SVM) classification strategy are considered. Simulations show promising results with both methods, with SVMs outperforming ANNs for the more demanding classification scenarios.