Search Results for author:
Found 57 papers, 24 papers with code
DeepXDE: A deep learning library for solving differential equations
We also present a Python library for PINNs, DeepXDE, which is designed to serve both as an education tool to be used in the classroom as well as a research tool for solving problems in computational science and engineering.
Physics-informed neural networks for inverse problems in nano-optics and metamaterials
In this paper we employ the emerging paradigm of physics-informed neural networks (PINNs) for the solution of representative inverse scattering problems in photonic metamaterials and nano-optics technologies.
Computational Physics Optics
Physics-informed neural networks with hard constraints for inverse design
We achieve the same objective as conventional PDE-constrained optimization methods based on adjoint methods and numerical PDE solvers, but find that the design obtained from hPINN is often simpler and smoother for problems whose solution is not unique.
Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
We tested gPINNs extensively and demonstrated the effectiveness of gPINNs in both forward and inverse PDE problems.
MIONet: Learning multiple-input operators via tensor product
Based on our theory and a low-rank approximation, we propose a novel neural operator, MIONet, to learn multiple-input operators.
Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transport
Deep neural operators can learn operators mapping between infinite-dimensional function spaces via deep neural networks and have become an emerging paradigm of scientific machine learning.
A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks
Hence, we have considered a total of 10 different sampling methods, including six non-adaptive uniform sampling, uniform sampling with resampling, two proposed adaptive sampling, and an existing adaptive sampling.
Reliable extrapolation of deep neural operators informed by physics or sparse observations
Deep neural operators can learn nonlinear mappings between infinite-dimensional function spaces via deep neural networks.
Fourier-MIONet: Fourier-enhanced multiple-input neural operators for multiphase modeling of geological carbon sequestration
Here, we develop a Fourier-enhanced multiple-input neural operator (Fourier-MIONet) to learn the solution operator of the problem of multiphase flow in porous media.
Fourier-DeepONet: Fourier-enhanced deep operator networks for full waveform inversion with improved accuracy, generalizability, and robustness
Here, we develop a Fourier-enhanced deep operator network (Fourier-DeepONet) for FWI with the generalization of seismic sources, including the frequencies and locations of sources.
SALMONN: Towards Generic Hearing Abilities for Large Language Models
Hearing is arguably an essential ability of artificial intelligence (AI) agents in the physical world, which refers to the perception and understanding of general auditory information consisting of at least three types of sounds: speech, audio events, and music.
DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
This universal approximation theorem is suggestive of the potential application of neural networks in learning nonlinear operators from data.
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
In addition to providing a standardized means of assessing performance, PINNacle also offers an in-depth analysis to guide future research, particularly in areas such as domain decomposition methods and loss reweighting for handling multi-scale problems and complex geometry.
Gated Multiple Feedback Network for Image Super-Resolution
The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era.
Ranked #18 on
Image Super-Resolution
on BSD100 - 4x upscaling
Enhancing Large Language Model with Self-Controlled Memory Framework
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
Systems Biology: Identifiability analysis and parameter identification via systems-biology informed neural networks
The dynamics of systems biological processes are usually modeled by a system of ordinary differential equations (ODEs) with many unknown parameters that need to be inferred from noisy and sparse measurements.
Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
Traditional data-driven deep learning models often struggle with high training costs, error accumulation, and poor generalizability in complex physical processes.
Learning Specialized Activation Functions for Physics-informed Neural Networks
To avoid the inefficient manual selection and to alleviate the optimization difficulty of PINNs, we introduce adaptive activation functions to search for the optimal function when solving different problems.
Towards Building Voice-based Conversational Recommender Systems: Datasets, Potential Solutions, and Prospects
Conversational recommender systems (CRSs) have become crucial emerging research topics in the field of RSs, thanks to their natural advantages of explicitly acquiring user preferences via interactive conversations and revealing the reasons behind recommendations.
Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models
Audio-visual large language models (LLM) have drawn significant attention, yet the fine-grained combination of both input streams is rather under-explored, which is challenging but necessary for LLMs to understand general video inputs.
PPDONet: Deep Operator Networks for Fast Prediction of Steady-State Solutions in Disk-Planet Systems
We develop a tool, which we name Protoplanetary Disk Operator Network (PPDONet), that can predict the solution of disk-planet interactions in protoplanetary disks in real-time.
Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness
To derive a meaningful bound, we study the generalization error of neural networks for classification problems in terms of data distribution and neural network smoothness.
Collapse of Deep and Narrow Neural Nets
However, here we show that even for such activation, deep and narrow neural networks (NNs) will converge to erroneous mean or median states of the target function depending on the loss with high probability.
Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
Here, we propose a new method with the objective of endowing the DNN with uncertainty quantification for both sources of uncertainty, i. e., the parametric uncertainty and the approximation uncertainty.
How to Host a Data Competition: Statistical Advice for Design and Analysis of a Data Competition
It also describes a post-competition analysis that enables robust and efficient assessment of the strengths and weaknesses of solutions from different competitors, as well as greater understanding of the regions of the input space that are well-solved.
Dying ReLU and Initialization: Theory and Numerical Examples
Numerical examples are provided to demonstrate the effectiveness of the new initialization procedure.
Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition
In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.
Operator learning for predicting multiscale bubble growth dynamics
Simulating and predicting multiscale problems that couple multiple physics and dynamics across many orders of spatiotemporal scales is a great challenge that has not been investigated systematically by deep neural networks (DNNs).
Computational Physics
Mixed graphs with smallest eigenvalue greater than $-\frac{\sqrt{5}+1}{2}$
The classical problem of characterizing the graphs with bounded eigenvalues may date back to the work of Smith in 1970.
Combinatorics 05C50
One-shot learning for solution operators of partial differential equations
Discovering governing equations of a physical system, represented by partial differential equations (PDEs), from data is a central challenge in a variety of areas of science and engineering.
Study of Proximal Normalized Subband Adaptive Algorithm for Acoustic Echo Cancellation
In addition, an adaptive approach for the choice of the thresholding parameter in the proximal step is also proposed based on the minimization of the mean square deviation.
A survey on active noise control techniques -- Part I: Linear systems
Active noise control (ANC) is an effective way for reducing the noise level in electroacoustic or electromechanical systems.
Active noise control techniques for nonlinear systems
Most of the literature focuses on the development of the linear active noise control (ANC) techniques.
Conjugate Gradient Adaptive Learning with Tukey's Biweight M-Estimate
We propose a novel M-estimate conjugate gradient (CG) algorithm, termed Tukey's biweight M-estimate CG (TbMCG), for system identification in impulsive noise environments.
Importance is in your attention: agent importance prediction for autonomous driving
Trajectory prediction is an important task in autonomous driving.
Inclusion in CSR Reports: The Lens from a Data-Driven Machine Learning Model
Inclusion, as one of the foundations in the diversity, equity, and inclusion initiative, concerns the degree of being treated as an ingroup member in a workplace.
Random Utterance Concatenation Based Data Augmentation for Improving Short-video Speech Recognition
One of limitations in end-to-end automatic speech recognition (ASR) framework is its performance would be compromised if train-test utterance lengths are mismatched.
Robust Andrew's sine estimate adaptive filtering
Two Andrew's sine estimator (ASE)-based robust adaptive filtering algorithms are proposed in this brief.
MedGPTEval: A Dataset and Benchmark to Evaluate Responses of Large Language Models in Medicine
The responses generated by chatbots based on LLMs are recorded for blind evaluations by five licensed medical experts.
Deep Learning for Solving and Estimating Dynamic Macro-Finance Models
We develop a methodology that utilizes deep learning to simultaneously solve and estimate canonical continuous-time general equilibrium models in financial economics.
CIF-PT: Bridging Speech and Text Representations for Spoken Language Understanding via Continuous Integrate-and-Fire Pre-Training
We also observe the cross-modal representation extracted by CIF-PT obtains better performance than other neural interfaces for the tasks of SLU, including the dominant speech representation learned from self-supervised pre-training.
PolyVoice: Language Models for Speech to Speech Translation
For the speech synthesis part, we adopt the existing VALL-E X approach and build a unit-based audio language model.
Text-only Domain Adaptation using Unified Speech-Text Representation in Transducer
Domain adaptation using text-only corpus is challenging in end-to-end(E2E) speech recognition.
LLM-Mini-CEX: Automatic Evaluation of Large Language Model for Diagnostic Conversation
Despite their alluring technological potential, there is no unified and comprehensive evaluation criterion, leading to the inability to evaluate the quality and potential risks of medical LLMs, further hindering the application of LLMs in medical treatment scenarios.
Connecting Speech Encoder and Large Language Model for ASR
Q-Former-based LLMs can generalise well to out-of-domain datasets, where 12% relative WER reductions over the Whisper baseline ASR model were achieved on the Eval2000 test set without using any in-domain training data from Switchboard.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
D2NO: Efficient Handling of Heterogeneous Input Function Spaces with Distributed Deep Neural Operators
Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems.
ROAM: memory-efficient large DNN training via optimized operator ordering and memory layout
However, a memory-efficient execution plan that includes a reasonable operator execution order and tensor memory layout can significantly increase the models' memory efficiency and reduce overheads from high-level techniques.
Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Planning Reliability Assurance Tests for Autonomous Vehicles
This paper aims to fill in this gap by developing statistical methods for planning AV reliability assurance tests based on recurrent events data.
A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model
Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem.
CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing
To bridge the gap between modalities, CoAVT employs a query encoder, which contains a set of learnable query embeddings, and extracts the most informative audiovisual features of the corresponding text.
Speeding up and reducing memory usage for scientific machine learning via mixed precision
Scientific machine learning (SciML) has emerged as a versatile approach to address complex computational science and engineering problems.
Challenges in Training PINNs: A Loss Landscape Perspective
This paper explores challenges in training Physics-Informed Neural Networks (PINNs), emphasizing the role of the loss landscape in the training process.
DIMON: Learning Solution Operators of Partial Differential Equations on a Diffeomorphic Family of Domains
DIMON is based on transporting a given problem (initial/boundary conditions and domain $\Omega_{\theta}$) to a problem on a reference domain $\Omega_{0}$, where training data from multiple problems is used to learn the map to the solution on $\Omega_{0}$, which is then re-mapped to the original domain $\Omega_{\theta}$.
Conformalized-DeepONet: A Distribution-Free Framework for Uncertainty Quantification in Deep Operator Networks
In this paper, we adopt conformal prediction, a distribution-free uncertainty quantification (UQ) framework, to obtain confidence prediction intervals with coverage guarantees for Deep Operator Network (DeepONet) regression.
