no code implementations • 7 Feb 2023 • J. Quetzalcoatl Toledo-Marin, James A. Glazier, Geoffrey Fox
Our results indicate that increasing the size of the training set has a substantial effect on reducing performance fluctuations and overall error.
no code implementations • 6 May 2021 • Endre T. Somogyi, Jeffery Coulter, Fanbo Sun, Herbert M. Sauro, James A. Glazier
Modeling and simulation (M&S) has revolutionized the way modern engineered products are designed, tested and evaluated.
1 code implementation • 10 Feb 2021 • J. Quetzalcóatl Toledo-Marín, Geoffrey Fox, James P. Sluka, James A. Glazier
To improve convergence during training, we apply a training approach that uses roll-back to reject stochastic changes to the network that increase the loss function.
1 code implementation • 9 Feb 2021 • J. Quetzalcoatl Toledo-Marin, James A. Glazier
The key point is that the set of quasi-eigenvectors form a basis set in latent space and each direction corresponds to a feature in real space.