Publications (27)
Exploring the Nexus of Many-Body Theories through Neural Network Techniques: the Tangent Model
Senwei Liang, Karol Kowalski, Chao Yang +1
In this paper, we present a physically informed neural network representation of the effective interactions associated with coupled-cluster downfolding models to describe chemical…
Probing reaction channels via reinforcement learning
Senwei Liang, Aditya N. Singh, Yuanran Zhu +2
We propose a reinforcement learning based method to identify important configurations that connect reactant and product states along chemical reaction paths. By shooting multiple t…
A Generic Shared Attention Mechanism for Various Backbone Neural Networks
Zhongzhan Huang, Senwei Liang, Mingfu Liang +1
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individua…
Drop-Activation: Implicit Parameter Reduction and Harmonic Regularization
Senwei Liang, Yuehaw Khoo, Haizhao Yang
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The…
Stationary Density Estimation of Itô Diffusions Using Deep Learning
Yiqi Gu, John Harlim, Senwei Liang +1
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 solutio…
Blending Pruning Criteria for Convolutional Neural Networks
Wei He, Zhongzhan Huang, Mingfu Liang +2
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 re…
Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
Senwei Liang, Zhongzhan Huang, Mingfu Liang +1
Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of…
Effective Many-body Interactions in Reduced-Dimensionality Spaces Through Neural Network Models
Senwei Liang, Karol Kowalski, Chao Yang +1
Accurately describing properties of challenging problems in physical sciences often requires complex mathematical models that are unmanageable to tackle head-on. Therefore, develop…
On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver
Zhongzhan Huang, Senwei Liang, Hong Zhang +2
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…
Quantifying Spatial Homogeneity of Urban Road Networks via Graph Neural Networks
Jiawei Xue, Nan Jiang, Senwei Liang +4
Quantifying the topological similarities of different parts of urban road networks (URNs) enables us to understand the urban growth patterns. While conventional statistics provide…
AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training
Zhongzhan Huang, Mingfu Liang, Senwei Liang +1
Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this probl…
Reproducing Activation Function for Deep Learning
Senwei Liang, Liyao Lyu, Chunmei Wang +1
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 e…
Finite Expression Method for Solving High-Dimensional Partial Differential Equations
Senwei Liang, Haizhao Yang
Designing efficient and accurate numerical solvers for high-dimensional partial differential equations (PDEs) remains a challenging and important topic in computational science and…
Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation
Xinkun Wang, Yifang Wang, Senwei Liang +7
This paper discusses how ophthalmologists often rely on multimodal data to improve diagnostic accuracy. However, complete multimodal data is rare in real-world applications due to…
H-FEX: A Symbolic Learning Method for Hamiltonian Systems
Jasen Lai, Senwei Liang, Chunmei Wang
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-drive…
Identifying Unknown Stochastic Dynamics via Finite expression methods
Senwei Liang, Chunmei Wang, Xingjian Xu
Modeling stochastic differential equations (SDEs) is crucial for understanding complex dynamical systems in various scientific fields. Recent methods often employ neural network-ba…
Efficient Attention Network: Accelerate Attention by Searching Where to Plug
Zhongzhan Huang, Senwei Liang, Mingfu Liang +2
Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (C…
Solving High-Dimensional Partial Integral Differential Equations: The Finite Expression Method
Gareth Hardwick, Senwei Liang, Haizhao Yang
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 FE…
Optimizing Shot Assignment in Variational Quantum Eigensolver Measurement
Linghua Zhu, Senwei Liang, Chao Yang +1
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…
The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network
Zhongzhan Huang, Senwei Liang, Mingfu Liang +3
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 netwo…
Artificial-Intelligence-Driven Shot Reduction in Quantum Measurement
Senwei Liang, Linghua Zhu, Xiaolin Liu +2
Variational Quantum Eigensolver (VQE) provides a powerful solution for approximating molecular ground state energies by combining quantum circuits and classical computers. However,…
Machine Learning for Prediction with Missing Dynamics
John Harlim, Shixiao W. Jiang, Senwei Liang +1
This article presents a general framework for recovering missing dynamical systems using available data and machine learning techniques. The proposed framework reformulates the pre…
QuGStep: Refining Step Size Selection in Gradient Estimation for Variational Quantum Algorithms
Senwei Liang, Linghua Zhu, Xiaosong Li +1
Variational quantum algorithms (VQAs) offer a promising approach to solving computationally demanding problems by combining parameterized quantum circuits with classical optimizati…
Learning Epidemiological Dynamics via the Finite Expression Method
Jianda Du, Senwei Liang, Chunmei Wang
Modeling and forecasting the spread of infectious diseases is essential for effective public health decision-making. Traditional epidemiological models rely on expert-defined frame…
Learning nonlinear integral operators via Recurrent Neural Networks and its application in solving Integro-Differential Equations
Hardeep Bassi, Yuanran Zhu, Senwei Liang +4
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-di…
Solving PDEs on Unknown Manifolds with Machine Learning
Senwei Liang, Shixiao W. Jiang, John Harlim +1
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…
DIANet: Dense-and-Implicit Attention Network
Zhongzhan Huang, Senwei Liang, Mingfu Liang +1
Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them…