From fat droplets to floating forests: cross-domain transfer learning using a PatchGAN-based segmentation model

no code implementations • 8 Nov 2022 • Kameswara Bharadwaj Mantha, Ramanakumar Sankar, Yuping Zheng, Lucy Fortson, Thomas Pengo, Douglas Mashek, Mark Sanders, Trace Christensen, Jeffrey Salisbury, Laura Trouille, Jarrett E. K. Byrnes, Isaac Rosenthal, Henry Houskeeper, Kyle Cavanaugh

We compare and contrast its performance with a TL model based on the COCO image set, and subsequently with baseline counterparts.

Transfer Learning

Constrained Langevin Algorithms with L-mixing External Random Variables

no code implementations • 27 May 2022 • Yuping Zheng, Andrew Lamperski

Langevin algorithms are gradient descent methods augmented with additive noise, and are widely used in Markov Chain Monte Carlo (MCMC) sampling, optimization, and machine learning.