Deep learning optimizes constellation for two-way relaying networks, boosting sum rate.
problem Optimizing constellation for better performance in two-way relaying networks.
method Deep neural networks (DNNs) trained to minimize cross entropy loss for direct constellation optimization.
result Significant performance gain in achievable sum rate compared to conventional relaying schemes.
DiffTaichi enables fast, differentiable physical simulations with shorter code.
problem Building efficient differentiable physical simulators.
method Differentiable programming language (DiffTaichi) that generates gradients using source code transformations and a light-weight tape.
result Differentiable physical simulators written in DiffTaichi are faster and more concise than existing methods.
Spatial separation of suspended particles based on contrast in their physical or chemical properties forms the basis of various biological assays performed on lab-on-achip devices. To electronically acquire this information, we have recently introduced a microfluidic sensing platform, called Microfluidic CODES, which c…
Machine learning predicts accurate cloning of printed graphical codes.
problem Clonability of anti-counterfeiting printable graphical codes.
method Simple system composed of fully connected neural network layers.
result Accurate estimation of digital codes from printed counterparts in certain cases.
This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling …
PGA neural network improves uncertainty quantification in lake temperature modeling.
problem Quantifying uncertainties in lake temperature models while maintaining physical consistency.
method Integrates physical constraints into neural networks using Monte Carlo Dropout.
result Ensures better generalizability and physical consistency in MC estimates.
jinns is a JAX library for physics-informed neural networks.
problem Physics-informed neural networks for forward and inverse problems.
method Physics-informed neural networks using JAX ecosystem.
result Efficient prototyping and extensions for real problems.
Constrained sequence codes have been widely used in modern communication and data storage systems. Sequences encoded with constrained sequence codes satisfy constraints imposed by the physical channel, hence enabling efficient and reliable transmission of coded symbols. Traditional encoding and decoding of constrained …
CoPhy-PGNN tackles competing PG losses in neural networks for solving eigenvalue problems.
problem Solving eigenvalue problems with competing physics-guided loss functions.
method Learning generalizable solutions using a novel approach to handle competing PG losses.
result Demonstrates the effectiveness of the approach in quantum mechanics and electromagnetic propagation.
Physics-informed neural networks struggle with stiffness leading to gradient imbalance.
problem Gradient pathologies in physics-informed neural networks.
method Learning rate annealing and novel neural network architecture.
result Significant improvement in predictive accuracy (50-100x) across various physics problems.
JAX MD enables differentiable physics simulations for molecular dynamics.
problem Performing efficient and differentiable physics simulations for molecular dynamics.
method Differentiable physics simulation environments, interaction potentials, neural networks, flexible primitives.
result Differentiable physics simulations can be used for meta-optimization and scaling to large particle systems.
Unified access package for fundamental physics datasets simplifies machine learning.
problem Lack of unified access to datasets from multiple fundamental physics disciplines.
method Unified Python package with common interface and reference models.
result Graph-based neural networks perform similarly to dedicated methods on various datasets.
Improved deep dynamics models with symmetries for better accuracy and generalization.
problem Limited physical accuracy and inability to generalize under distributional shift in deep learning dynamics models.
method Incorporating symmetries into convolutional neural networks using various methods tailored to enforce different symmetries.
result Models robust to distributional shift by symmetry group transformations and favorable sample complexity.
p3VAE combines physics and machine learning for robust data representations.
problem Improving machine learning models' robustness to environmental factors of variation.
method Physics-informed variational autoencoder integrating physical knowledge with neural networks.
result p3VAE outperforms competing models in extrapolation and interpretability. AutoKE automates embedding physical knowledge into neural networks for complex engineering problems.
problem Complex physical equations in engineering problems.
method AutoKE framework using deep neural networks, equation parsing, automatic differentiation, adaptive weights, and NAS.
result Automatically embeds physical knowledge into neural networks for complex equations efficiently.
New PINN architectures learn high-frequency features using Fourier features.
problem PINNs struggle with high-frequency or multi-scale features.
method Employ spatio-temporal and multi-scale random Fourier features.
result Effective PINN models for multi-scale PDEs.
Paper improves PINNs' extrapolation by TL and adaptive AFs.
problem PINNs' poor extrapolation performance and sensitivity to AFs.
method Transfer learning within an extended domain and adaptive activation functions.
result Average 40% reduction in relative L2 error and 50% in mean absolute error in extrapolation domain.
VED framework learns low-dimensional latent representations of physical systems.
problem Learning latent representations of complex physical systems.
method Variational Encoder-Decoder (VED) framework with KL divergence and covariance regularization.
result VED achieves lower-dimensional latent representations with improved feature disentanglement.
Three physics-constrained regression exercises for image velocimetry and turbulence modeling.
problem Image velocimetry and turbulence modeling challenges.
method Physics-constrained regression exercises implemented as toy problems.
result Python codes provided for all exercises.
Framework augments physical models with deep learning for complex dynamics forecasting.
problem Forecasting complex dynamical phenomena with partial knowledge.
method APHYNITY framework: decomposes dynamics into physical and data-driven components.
result Framework accurately forecasts system evolution and identifies relevant parameters.
A new algorithm speeds up neural network derivative calculations.
problem Exponential runtime of autodifferentiation for high-order derivatives in neural networks.
method n-TangentProp, a quasilinear algorithm for computing higher-order derivatives.
result Computes exact derivatives in quasilinear time, not exponential.
CODE learns ODE dynamics from sparse data, outperforming neural and kernel methods.
problem Learning ODE dynamics from sparse and noisy data.
method CODE uses Polynomial Chaos Expansion (aPCE) for the ODE's RHS, enabling global orthonormal polynomial representation.
result CODE exhibits remarkable extrapolation capabilities even under novel initial conditions and measurement noise.
We propose weight-sharing regularization for neural networks.
problem Training fully connected networks with shuffled pixel data.
method Introduce a regularization penalty on weights and design parallel algorithms.
result Weight-sharing regularization enables learning convolution-like filters.
Algorithm learns latent variables for thermodynamically-consistent deep neural networks.
problem Predicting time evolution of large-scale physical systems with thermodynamic consistency.
method Sparse autoencoders and structure-preserving neural networks.
result Method conserves total energy and entropy inequality for both conservative and dissipative systems.
ASLA learns atomic structures using neural networks and reinforcement learning.
problem Designing materials and drugs with desired properties.
method Atomistic structure learning algorithm (ASLA) using a convolutional neural network and reinforcement learning.
result ASLA can predict optimal structural arrangements of atoms for various target properties.
PHYRE benchmark tests physics learning algorithms.
problem Developing efficient algorithms for physics reasoning.
method Simple classical mechanics puzzles in a 2D environment.
result Modern algorithms perform poorly on PHYRE.
Improved neural network surrogates for ICF using manifold and cycle consistency.
problem Modeling and predicting complex physical processes in inertial confinement fusion.
method Training neural network surrogates that are consistent with the physical manifold and cyclically consistent.
result Surrogates are superior in predictive performance, more resilient to sampling artifacts, and more data efficient.
Soft-constrained PINN solves ODEs with minimal data, improving efficiency and robustness.
problem Sparse and noisy data in experiments and simulations.
method Soft-constrained Physics-informed Neural Network (PINN) with minimal labeled data.
result Soft-constrained PINN reduces need for labeled data and achieves strong generalization.
We develop a new method to solve complex physics equations more accurately and efficiently.
problem Challenges in solving functional differential equations due to high computational costs and inaccurate approximations.
method Combining physics-informed neural networks (PINNs) with cylindrical approximation to handle functional derivatives.
result Our method achieves typical L1 relative error orders of PINNs of ∼10−3 on two FDEs. CAZSL learns to generalize physical interactions from context.
problem Designing models that can generalize over unknown objects during manipulation.
method Context-aware zero-shot learning using Siamese network architecture, embedding space masking, and regularization.
result CAZSL models can generalize to different parameters or features of interacting objects.
Proposes neural networks for solving complex free boundary problems.
problem Solving free boundary and Stefan problems with complex interfaces.
method Physics-informed neural networks for approximating solutions and boundaries.
result Successfully approximates solutions and moving boundaries in various Stefan problems.
Physics-informed DeepONets solve PDEs without paired data, predicting solutions quickly.
problem Lack of paired input-output data for solving PDEs.
method Physics-informed DeepONets use automatic differentiation to enforce physical laws as soft penalty constraints.
result Physics-informed DeepONets can solve PDEs without paired data, predicting solutions up to 3 orders of magnitude faster.
Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system's constituent parts. In this work, we introduce the neural relational inference (NRI…
In this work, sequence-to-sequence (seq2seq) models, originally developed for language translation, are used to predict the temporal evolution of complex, multi-physics computer simulations. The predictive performance of seq2seq models is compared to state transition models for datasets generated with multi-physics cod…
PFPN uses particle filtering to improve character control in physics-based simulations.
problem Premature commitment to suboptimal actions in high-dimensional continuous control problems for articulated characters.
method Proposes a particle-based action policy using particle filtering to dynamically explore and discretize the action space.
result Demonstrates better imitation performance and robustness to external perturbations compared to Gaussian policies.
PhyDNN uses physics knowledge to improve drag force prediction models.
problem Complex physical processes in fluid dynamics are hard to model accurately.
method Physics-guided structural priors and aggregate supervision for deep learning.
result PhyDNN achieves a significant 8.46% improvement in drag force prediction.
New quantum codes improve error correction with local tests.
problem Improving quantum error correction efficiency.
method Introducing hemicubic codes and exploiting their local testability.
result Quantum codes with improved local testability and error correction.
We present a novel probabilistic programming framework that couples directly to existing large-scale simulators through a cross-platform probabilistic execution protocol, which allows general-purpose inference engines to record and control random number draws within simulators in a language-agnostic way. The execution …
HECT tests climate model outputs for reproducibility.
problem Ensuring climate models accurately reflect physical processes.
method Probabilistic classifiers for high-dimensional spatio-temporal data.
result A principled way to assess statistical reproducibility of climate models.
PICN learns physical fields from shallow neural networks, improving AI in multi-physical systems.
problem Challenges in modeling and forecasting multi-physical systems due to data scarcity and noise.
method Physics-informed convolutional network (PICN) combining CNN and physical laws, using deconvolution and convolution layers.
result PICN effectively solves and estimates nonlinear physical operator equations and recovers physical information from noisy observations.
WeldNet reduces complex dynamics to simpler, manageable segments.
problem Complex, high-dimensional time-dependent datasets from physical processes are costly to simulate.
method Windowed Encoders for Learning Dynamics, splitting time domain into windows for nonlinear dimension reduction and propagator training.
result WeldNet captures nonlinear latent structures and dynamics, outperforming existing methods.
PID-GAN uses physics knowledge to improve deep learning models' reliability.
problem Improving deep learning models' reliability in physics-based applications.
method Physics-informed GAN architecture that incorporates physics knowledge into both generator and discriminator models.
result PID-GAN framework outperforms state-of-the-art in handling gradient imbalance.
New method identifies physical constants from video data alone.
problem Identifying physical constants from video data.
method Proves level-set slope-coverage condition ensures local affine mapping to true physical state, enabling exact parameter recovery.
result Underdamped systems identifiable from a single video clip, other regimes require three diverse trajectories.
TreeCaps improves code comprehension for software developers.
problem Processing code efficiently for software developers.
method Tree-based capsule networks for capturing code syntactical structures and dependencies.
result TreeCaps outperforms other approaches in classifying program functionalities.
FunDiff models physical functions using diffusion and autoencoders.
problem Adapting generative models to continuous physical functions.
method Combines latent diffusion with function autoencoder, enforcing physical priors.
result Achieves optimal convergence rates for physical function estimation.
We describe tests validating progress made toward acceleration and automation of hydrodynamic codes in the regime of developed turbulence by three Deep Learning (DL) Neural Network (NN) schemes trained on Direct Numerical Simulations of turbulence. Even the bare DL solutions, which do not take into account any physics …
ConfFlow uses transformer networks to generate molecular conformations efficiently.
problem Efficient generation of valid conformations for large molecules.
method Flow-based model using transformer networks that directly samples in coordinate space.
result ConfFlow improves accuracy by up to 40% for large molecule conformations.
MPP trains a transformer to predict multiple physical systems, improving accuracy across various tasks.
problem Training models for specific physical systems is inefficient and requires fine-tuning.
method MPP trains a shared transformer on multiple heterogeneous physical systems, projecting fields into a shared embedding space.
result A single MPP-pretrained transformer outperforms task-specific models on all pretraining sub-tasks and downstream tasks.