Optimizing the optimizer for data driven deep neural networks and physics informed neural networks

no code implementations • 16 May 2022 • John Taylor, Wenyi Wang, Biswajit Bala, Tomasz Bednarz

We investigate the role of the optimizer in determining the quality of the model fit for neural networks with a small to medium number of parameters.

Exploiting the Power of Levenberg-Marquardt Optimizer with Anomaly Detection in Time Series

no code implementations • 11 Nov 2021 • Wenyi Wang, John Taylor, Biswajit Bala

Literature reviews have shown that the LM can be very powerful and effective on moderate function approximation problems when the number of weights in the network is not more than a couple of hundred.

Anomaly Detection Change Detection +2