An automation approach in dielectric constant prediction using machine learning

This paper aims at predicting dielectric constants of metal with respect to temperature interval at certain frequency using Feed forward back propagation networks, Nonlinear autoregressive exogenous inputs networks and various other algorithms. Calculating the dielectric constant is crucial in the field of engineering; up till now this task is done by manual experiments. Though there are many existing experimental approaches for predicting dielectric constant but no such established algorithms exist that can automate the process of prediction. Through this paper multiple machine learning techniques are applied for predicting dielectric constant; also to improve the correlation between the input attributes optimization is performed.