Senwei Liang
YOU?
Author Swipe
View article: QuGStep: Refining step size selection in gradient estimation for variational quantum algorithms
QuGStep: Refining step size selection in gradient estimation for variational quantum algorithms Open
Variational quantum algorithms (VQAs) offer a promising approach to solving computationally demanding problems by combining parameterized quantum circuits with classical optimization. Estimating probabilistic outcomes on quantum hardware r…
View article: H-FEX: A Symbolic Learning Method for Hamiltonian Systems
H-FEX: A Symbolic Learning Method for Hamiltonian Systems Open
Hamiltonian systems describe a broad class of dynamical systems governed by Hamiltonian functions, which encode the total energy and dictate the evolution of the system. Data-driven approaches, such as symbolic regression and neural networ…
View article: Exploring the nexus of many-body theories through neural network techniques: the tangent model
Exploring the nexus of many-body theories through neural network techniques: the tangent model Open
In this paper, we present a physically informed neural network (NN) representation of the effective interactions associated with coupled-cluster downfolding models to describe chemical systems and processes. The NN representation not only …
View article: Identifying Unknown Stochastic Dynamics via Finite expression methods
Identifying Unknown Stochastic Dynamics via Finite expression methods Open
Modeling stochastic differential equations (SDEs) is crucial for understanding complex dynamical systems in various scientific fields. Recent methods often employ neural network-based models, which typically represent SDEs through a combin…
View article: Exploring the Nexus of Many-Body Theories through Neural Network Techniques: the Tangent Model
Exploring the Nexus of Many-Body Theories through Neural Network Techniques: the Tangent Model Open
In this paper, we present a physically informed neural network representation of the effective interactions associated with coupled-cluster downfolding models to describe chemical systems and processes. The neural network representation no…
View article: Learning Epidemiological Dynamics via the Finite Expression Method
Learning Epidemiological Dynamics via the Finite Expression Method Open
Modeling and forecasting the spread of infectious diseases is essential for effective public health decision-making. Traditional epidemiological models rely on expert-defined frameworks to describe complex dynamics, while neural networks, …
View article: Effective many-body interactions in reduced-dimensionality spaces through neural network models
Effective many-body interactions in reduced-dimensionality spaces through neural network models Open
Accurately describing properties of challenging problems in physical sciences often requires complex mathematical models that are unmanageable to tackle head on. Therefore, developing reduced-dimensionality representations that encapsulate…
View article: A Comparative Study of Pattern Recognition Models on the PaviaU Dataset
A Comparative Study of Pattern Recognition Models on the PaviaU Dataset Open
This report provides a comprehensive study focused on land cover classification and remote sensing image analysis using the PaviaU dataset. The report first introduces the basic characteristics and application background of the data set, a…
View article: Artificial-intelligence-driven shot reduction in quantum measurement
Artificial-intelligence-driven shot reduction in quantum measurement Open
Variational Quantum Eigensolver (VQE) provides a powerful solution for approximating molecular ground state energies by combining quantum circuits and classical computers. However, estimating probabilistic outcomes on quantum hardware requ…
View article: Solving High-Dimensional Partial Integral Differential Equations: The Finite Expression Method
Solving High-Dimensional Partial Integral Differential Equations: The Finite Expression Method Open
In this paper, we introduce a new finite expression method (FEX) to solve high-dimensional partial integro-differential equations (PIDEs). This approach builds upon the original FEX and its inherent advantages with new advances: 1) A novel…
View article: Effective Many-body Interactions in Reduced-Dimensionality Spaces Through Neural Network Models
Effective Many-body Interactions in Reduced-Dimensionality Spaces Through Neural Network Models Open
Accurately describing properties of challenging problems in physical sciences often requires complex mathematical models that are unmanageable to tackle head-on. Therefore, developing reduced dimensionality representations that encapsulate…
View article: Artificial-Intelligence-Driven Shot Reduction in Quantum Measurement
Artificial-Intelligence-Driven Shot Reduction in Quantum Measurement Open
Variational Quantum Eigensolver (VQE) provides a powerful solution for approximating molecular ground state energies by combining quantum circuits and classical computers. However, estimating probabilistic outcomes on quantum hardware requ…
View article: Learning nonlinear integral operators via recurrent neural networks and its application in solving integro-differential equations
Learning nonlinear integral operators via recurrent neural networks and its application in solving integro-differential equations Open
In this paper, we propose using LSTM-RNNs (Long Short-Term Memory-Recurrent Neural Networks) to learn and represent nonlinear integral operators that appear in nonlinear integro-differential equations (IDEs). The LSTM-RNN representation of…
View article: Learning nonlinear integral operators via Recurrent Neural Networks and its application in solving Integro-Differential Equations
Learning nonlinear integral operators via Recurrent Neural Networks and its application in solving Integro-Differential Equations Open
In this paper, we propose using LSTM-RNNs (Long Short-Term Memory-Recurrent Neural Networks) to learn and represent nonlinear integral operators that appear in nonlinear integro-differential equations (IDEs). The LSTM-RNN representation of…
View article: Probing reaction channels via reinforcement learning
Probing reaction channels via reinforcement learning Open
Chemical reactions are dynamical processes involving the correlated reorganization of atomic configurations, driving the conversion of an initial reactant into a result product. By virtue of the metastability of both the reactants and prod…
View article: On fast simulation of dynamical system with neural vector enhanced numerical solver
On fast simulation of dynamical system with neural vector enhanced numerical solver Open
The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of step sizes when estimating integration, resulting in a trad…
View article: Optimizing Shot Assignment in Variational Quantum Eigensolver Measurement
Optimizing Shot Assignment in Variational Quantum Eigensolver Measurement Open
The rapid progress in quantum computing has opened up new possibilities for tackling complex scientific problems. Variational quantum eigensolver (VQE) holds the potential to solve quantum chemistry problems and achieve quantum advantages.…
View article: Probing reaction channels via reinforcement learning
Probing reaction channels via reinforcement learning Open
We propose a reinforcement learning based method to identify important configurations that connect reactant and product states along chemical reaction paths. By shooting multiple trajectories from these configurations, we can generate an e…
View article: A Generic Shared Attention Mechanism for Various Backbone Neural Networks
A Generic Shared Attention Mechanism for Various Backbone Neural Networks Open
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individually incorporate newly designed self-attention modules (SAMs…
View article: On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver
On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver Open
The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines. However, traditional numerical solvers are limited by the choice of step sizes when estimating integration, resulting in a trad…
View article: The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network
The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network Open
Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs). In general, previous works ignore where to plug…
View article: Finite Expression Method for Solving High-Dimensional Partial Differential Equations
Finite Expression Method for Solving High-Dimensional Partial Differential Equations Open
Designing efficient and accurate numerical solvers for high-dimensional partial differential equations (PDEs) remains a challenging and important topic in computational science and engineering, mainly due to the "curse of dimensionality" i…
View article: Quantifying the spatial homogeneity of urban road networks via graph neural networks
Quantifying the spatial homogeneity of urban road networks via graph neural networks Open
Publication: Quantifying the spatial homogeneity of urban road networks via graph neural networks, Nature Machine Intelligence, 2022. Publication DOI: 10.1038/s42256-022-00462-y Please refer to https://github.com/jiang719/road-network-pred…
View article: Quantifying the spatial homogeneity of urban road networks via graph neural networks
Quantifying the spatial homogeneity of urban road networks via graph neural networks Open
Publication: Quantifying the spatial homogeneity of urban road networks via graph neural networks, Nature Machine Intelligence, 2022. Publication DOI: 10.1038/s42256-022-00462-y Please refer to https://github.com/jiang719/road-network-pred…
View article: Stationary Density Estimation of Itô Diffusions Using Deep Learning
Stationary Density Estimation of Itô Diffusions Using Deep Learning Open
In this paper, we consider the density estimation problem associated with the stationary measure of ergodic Itô diffusions from a discrete-time series that approximate the solutions of the stochastic differential equations. To take an adva…
View article: AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training
AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training Open
Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this problem. Some of these methods achieved considerable performance…
View article: Blending Pruning Criteria for Convolutional Neural Networks
Blending Pruning Criteria for Convolutional Neural Networks Open
The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict requirement for real-world deployment. To overcome this, the …
View article: Solving PDEs on Unknown Manifolds with Machine Learning
Solving PDEs on Unknown Manifolds with Machine Learning Open
This paper proposes a mesh-free computational framework and machine learning theory for solving elliptic PDEs on unknown manifolds, identified with point clouds, based on diffusion maps (DM) and deep learning. The PDE solver is formulated …
View article: Reproducing Activation Function for Deep Learning
Reproducing Activation Function for Deep Learning Open
We propose reproducing activation functions (RAFs) to improve deep learning accuracy for various applications ranging from computer vision to scientific computing. The idea is to employ several basic functions and their learnable linear co…