Answers are grounded in this paper and cite their sources.
This letter presents a simple and effective technique allowing neural network based microwave models to be used outside their training range. Our technique detects necessity of extrapolation inside each hidden neuron and performs extrapolation using a modified neuron activation function. Compared to existing techniques, the proposed technique is easy to implement and the extrapolation result is equally good or better. Examples of extrapolating neural models of a high electron mobility transistor and a power amplifier are presented.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2010) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: