Soumik Sarkar

TL;DR: This work reformulate the microstructure design process using a constrained generative adversarial network (GAN) model that explicitly encodes invariance constraints within GANs to generate two-phase morphologies for photovoltaic applications obeying design specifications: specifically, user-defined short-circuit current density and fill factor combinations.

TL;DR: The crux of the idea is to train a deep convolutional autoencoder to suppress undesired parts of an image frame while allowing the desired parts resulting in efficient object detection.

TL;DR: This work solves a high-dimensional one-to-many inverse mapping problem concerning microfluidic flow sculpting, where the use of deep learning methods as an inverse map is very seldom explored and serves as a fruitful use-case to applied scientists and engineers in how deep learning can be beneficial as a solution for high- dimensional physical problems.

TL;DR: This work proposes a novel deep learning architecture, called spatiotemporal attention mechanism (STAM), for simultaneous learning of the most important time steps and variables and shows that STAM maintains state-of-the-art prediction accuracy while offering the benefit of accurate spatiotmporal interpretability.

TL;DR: In this article, a spatiotemporal pattern network (STPN) is proposed for energy/power prediction for complex dynamical systems. But the authors focus on the energy disaggregation context and use convex programming techniques beyond the STPN framework to achieve improved disaggregation performance.