In this effort, we propose a new deep architecture utilizing residual blocks inspired by implicit discretization schemes. As opposed to the standard feed-forward networks, the outputs of the proposed implicit residual blocks are defined as the fixed points of the appropriately chosen nonlinear transformations. We show that this choice leads to the improved stability of both forward and backward propagations, has a favorable impact on the generalization power, and allows for control the robustness of the network with only a few hyperparameters. In addition, the proposed reformulation of ResNet does not introduce new parameters and can potentially lead to a reduction in the number of required layers due to improved forward stability. Finally, we derive the memory-efficient training algorithm, propose a stochastic regularization technique, and provide numerical results in support of our findings.

Commercial refrigeration systems currently utilize refrigerants with global warming potential (GWP) values ranging from 1250 to 4000. The advent of low GWP alternatives (GWP $<150$) is expected to significantly curtail direct emissions from this segment and greatly influence the ongoing electrification and decarbonization efforts. Most of the low GWP alternatives exhibit flammability risk and hence require robust sensing solutions for a reliable and safe operation of the equipment. This review article aims to provide an overview of different sensing mechanisms suitable for potential applications in systems employing flammable refrigerants, particularly those designated as A2L class. A summary of different A2L refrigerants and their properties is provided followed by a broad review of different classes of sensors, their working principle, transduction method, features, advantages, and limitations. Additionally, key performance characteristics of accuracy, selectivity, sensitivity, dynamic characteristic, and durability among other properties are discussed. Finally, areas of improvement and corresponding approaches are suggested for potential sensors in the successful adoption of A2L class refrigerants.

We introduce a computational framework that integrates artificial intelligence (AI), machine learning, and high-performance computing to enable real-time steering of neutron scattering experiments using an edge-to-exascale workflow. Focusing on time-of-flight neutron event data at the Spallation Neutron Source, our approach combines temporal processing of four-dimensional neutron event data with predictive modeling for multidimensional crystallography. At the core of this workflow is the Temporal Fusion Transformer model, which provides voxel-level precision in predicting 3D neutron scattering patterns. The system incorporates edge computing for rapid data preprocessing and exascale computing via the Frontier supercomputer for large-scale AI model training, enabling adaptive, data-driven decisions during experiments. This framework optimizes neutron beam time, improves experimental accuracy, and lays the foundation for automation in neutron scattering. Although real-time experiment steering is still in the proof-of-concept stage, the demonstrated potential of this system offers a substantial reduction in data processing time from hours to minutes via distributed training, and significant improvements in model accuracy, setting the stage for widespread adoption across neutron scattering facilities and more efficient exploration of complex material systems.

We explore different methods of solving systems of stochastic differential equations by first implementing the Euler-Maruyama and Milstein methods with a Monte Carlo simulation on a CPU. The performance of the methods is significantly improved through the recently developed antithetic multilevel Monte Carlo estimator, which yields a computation complexity of O(epsilon(-2)) root-mean-square error and does so without the approximation of Levy areas. Further improvements in performance are gained by moving the algorithms to a GPU - first on a single device and then on a multi-GPU cluster. Our GPU implementation of the antithetic multilevel Monte Carlo displays a major speedup in computation when compared with many commonly used approaches in the literature. While our work is focused on the simulation of the stochastic volatility and interest rate model, it is easily extendable to other stochastic systems, and it is of particular interest to those with non-diagonal, non-commutative noise.