Related papers: Combining SchNet and SHARC: The SchNarc machine le…
Excited-state properties of highly correlated systems are key to understanding photosynthesis, luminescence, and the development of novel optical materials, but accurately capturing their interactions is computationally costly. We present…
In recent years, machine learning has been used to create data-driven solutions to problems for which an algorithmic solution is intractable, as well as fine-tuning existing algorithms. This research applies machine learning to the…
High-fidelity quantum dynamics emulators can be used to predict the time evolution of complex physical systems. Here, we introduce an efficient training framework for constructing machine learning-based emulators. Our approach is based on…
The Dicke-Ising model, one of the few paradigmatic models of matter-light interaction, exhibits a superradiant quantum phase transition above a critical coupling strength. However, in natural optical systems, its experimental validation is…
Neural network modules conditioned by known priors can be effectively trained and combined to represent systems with nonlinear dynamics. This work explores a novel formulation for data-efficient learning of deep control-oriented nonlinear…
Nonadiabaticity, i.e., the effect of mixing electronic states by nuclear motion, is a central phenomenon in molecular science. The strongest nonadiabatic effects arise due to the presence of conical intersections of electronic energy…
Inferring behavior model of a running software system is quite useful for several automated software engineering tasks, such as program comprehension, anomaly detection, and testing. Most existing dynamic model inference techniques are…
Understanding the quantum dynamics of strongly coupled molecule-cavity systems remains a significant challenge in molecular polaritonics. This work develops a comprehensive self-consistent model simulating electromagnetic interactions of…
Deep artificial neural networks are powerful tools with many possible applications in nanophotonics. Here, we demonstrate how a deep neural network can be used as a fast, general purpose predictor of the full near-field and far-field…
The accurate quantification of wall-shear stress dynamics is of substantial importance for various applications in fundamental and applied research, spanning areas from human health to aircraft design and optimization. Despite significant…
In recent years, deep learning (DL) techniques have provided state-of-the-art performance on different medical imaging tasks. However, the availability of good quality annotated medical data is very challenging due to involved time…
Excited states in single quantum dots (QDs) have been shown to be useful for spin state initialization and manipulation. For scalable quantum information processing it is necessary to have multiple spins interacting. Therefore, we present…
In this article, we present an efficient deep learning method called coupled deep neural networks (CDNNs) for coupled physical problems. Our method compiles the interface conditions of the coupled PDEs into the networks properly and can be…
With access to large datasets, deep neural networks (DNN) have achieved human-level accuracy in image and speech recognition tasks. However, in chemistry, data is inherently small and fragmented. In this work, we develop an approach of…
In this work, we use the artificial neural network (ANN) method to study and predict the distribution of strong coupling constants by fitting the existing data. Our approach takes advantage of the ability of ANN to learn complex nonlinear…
We develop a unified theoretical framework for the efficient description of multiphoton states generated and propagating in loop-based optical networks which contain nonlinear elements. These active optical components are modeled as…
Humans and most animals inherently possess a distinctive capacity to continually acquire novel experiences and accumulate worldly knowledge over time. This ability, termed continual learning, is also critical for deep neural networks (DNNs)…
Accurately measuring liquid dynamic viscosity across a wide range of shear rates, from the linear-response to shear-thinning regimes, presents significant experimental challenges due to limitations in resolving high shear rates and…
We have developed a numerical differentiation scheme which eliminates evaluation of overlap determinants in calculating the time-derivative non-adiabatic couplings (TDNACs). Evaluation of these determinants was the bottleneck in previous…
We present and evaluate a new deep neural network architecture for automatic thoracic disease detection on chest X-rays. Deep neural networks have shown great success in a plethora of visual recognition tasks such as image classification…